Machine Learning on Physical Robots
|
|
- Caitlin Henry
- 5 years ago
- Views:
Transcription
1 Machine Learning on Physical Robots Alfred P. Sloan Research Fellow Department or Computer Sciences The University of Texas at Austin
2 Research Question To what degree can autonomous intelligent agents learn in the presence of teammates and/or adversaries in real-time, dynamic domains?
3 Research Question To what degree can autonomous intelligent agents learn in the presence of teammates and/or adversaries in real-time, dynamic domains? Autonomous agents Multiagent systems Machine learning Robotics
4 Autonomous Intelligent Agents They must sense their environment. They must decide what action to take ( think ). They must act in their environment.
5 Autonomous Intelligent Agents They must sense their environment. They must decide what action to take ( think ). They must act in their environment. Complete Intelligent Agents
6 Autonomous Intelligent Agents They must sense their environment. They must decide what action to take ( think ). They must act in their environment. Complete Intelligent Agents Interact with other agents (Multiagent systems)
7 Autonomous Intelligent Agents They must sense their environment. They must decide what action to take ( think ). They must act in their environment. Complete Intelligent Agents Interact with other agents (Multiagent systems) Improve performance from experience (Learning agents)
8 Autonomous Intelligent Agents They must sense their environment. They must decide what action to take ( think ). They must act in their environment. Complete Intelligent Agents Interact with other agents (Multiagent systems) Improve performance from experience (Learning agents) Autonomous Bidding, Cognitive Systems, Traffic management, Robot Soccer
9 RoboCup
10 RoboCup Goal: By the year 2050, a team of humanoid robots that can beat the human World Cup champion team.
11 RoboCup Goal: By the year 2050, a team of humanoid robots that can beat the human World Cup champion team. An international research initiative
12 RoboCup Goal: By the year 2050, a team of humanoid robots that can beat the human World Cup champion team. An international research initiative Drives research in many areas: Control algorithms; machine vision, sensing; localization; Distributed computing; real-time systems; Ad hoc networking; mechanical design;
13 RoboCup Goal: By the year 2050, a team of humanoid robots that can beat the human World Cup champion team. An international research initiative Drives research in many areas: Control algorithms; machine vision, sensing; localization; Distributed computing; real-time systems; Ad hoc networking; mechanical design; Multiagent systems; machine learning; robotics
14 RoboCup Goal: By the year 2050, a team of humanoid robots that can beat the human World Cup champion team. An international research initiative Drives research in many areas: Control algorithms; machine vision, sensing; localization; Distributed computing; real-time systems; Ad hoc networking; mechanical design; Multiagent systems; machine learning; robotics Several Different Leagues
15 RoboCup Soccer
16 Sony Aibo (ERS-210A, ERS-7)
17 Sony Aibo (ERS-210A, ERS-7)
18 Sony Aibo (ERS-210A, ERS-7)
19 Creating a team Subtasks
20 Creating a team Subtasks Vision Localization Walking Ball manipulation (kicking) Individual decision making Communication/coordination
21 Creating a team Subtasks Vision Localization Walking Ball manipulation (kicking) Individual decision making Communication/coordination
22 Competitions Barely closed the loop by American Open (May, 03)
23 Competitions Barely closed the loop by American Open (May, 03) Improved significantly by Int l RoboCup (July, 03)
24 Competitions Barely closed the loop by American Open (May, 03) Improved significantly by Int l RoboCup (July, 03) Won 3rd place at US Open (2004, 2005) Quarterfinalist at RoboCup (2004, 2005)
25 Competitions Barely closed the loop by American Open (May, 03) Improved significantly by Int l RoboCup (July, 03) Won 3rd place at US Open (2004, 2005) Quarterfinalist at RoboCup (2004, 2005) Highlights: Many saves: 1; 2; 3; 4; Lots of goals: CMU; Penn; Penn; Germany; A nice clear A counterattack goal
26 Post-competition: the research
27 Post-competition: the research Model-based joint control [Stronger, S, 04] Learning sensor and action models [Stronger, S, 06] Machine learning for fast walking [Kohl, S, 04] Learning to acquire the ball [Fidelman, S, 06] Color constancy on mobile robots [Sridharan, S, 04] Robust particle filter localization [Sridharan, Kuhlmann, S, 05] Autonomous Color Learning [Sridharan, S, 05]
28 Learned Actuator/Sensor Models Mobile robots rely on models of their actions and sensors Typically tuned manually: Time-consuming
29 Learned Actuator/Sensor Models Mobile robots rely on models of their actions and sensors Typically tuned manually: Time-consuming Autonomous Sensor and Actuator Model Induction (ASAMI)
30 Learned Actuator/Sensor Models Mobile robots rely on models of their actions and sensors Typically tuned manually: Time-consuming Autonomous Sensor and Actuator Model Induction (ASAMI) ASAMI is autonomous: no external feedback Developmental robotics
31 Learned Actuator/Sensor Models Mobile robots rely on models of their actions and sensors Typically tuned manually: Time-consuming Autonomous Sensor and Actuator Model Induction (ASAMI) ASAMI is autonomous: no external feedback Developmental robotics Implemented and validated on Aibo ERS-7
32 The Task distance sensor input Sensor model: beacon height in image distance Mapping motivated by camera specs not accurate
33 The Task distance sensor input Sensor model: beacon height in image distance Mapping motivated by camera specs not accurate Action model: parametrized walking, W(x) velocity W(0) steps in place W(-300) has velocity -300 W(300) has velocity 300
34 Experimental Setup Aibo alternates walking forwards and backwards Forwards: random action in [0, 300] Backward phase: random action in [ 300, 0] Switch based on beacon size in image
35 Experimental Setup Aibo alternates walking forwards and backwards Forwards: random action in [0, 300] Backward phase: random action in [ 300, 0] Switch based on beacon size in image Aibo keeps self pointed at beacon
36 Learning Action and Sensor Models Both models provide info about the robot s location Sensor model: observation obs k location: x s (t k ) = S(obs k )
37 Learning Action and Sensor Models Both models provide info about the robot s location Sensor model: observation obs k location: x s (t k ) = S(obs k ) Action model: action command C(t) velocity: x a (t) = x(0) + t A(C(s)) ds 0
38 Learning Action and Sensor Models Both models provide info about the robot s location Sensor model: observation obs k location: x s (t k ) = S(obs k ) Action model: action command C(t) velocity: x a (t) = x(0) + t A(C(s)) ds 0 Goal: learn arbitrary continuous functions, A and S
39 Learning Action and Sensor Models Both models provide info about the robot s location Sensor model: observation obs k location: x s (t k ) = S(obs k ) Action model: action command C(t) velocity: x a (t) = x(0) + t A(C(s)) ds 0 Goal: learn arbitrary continuous functions, A and S Use polynomial regression as function approximator
40 Learning Action and Sensor Models Both models provide info about the robot s location Sensor model: observation obs k location: x s (t k ) = S(obs k ) Action model: action command C(t) velocity: x a (t) = x(0) + t A(C(s)) ds 0 Goal: learn arbitrary continuous functions, A and S Use polynomial regression as function approximator Models learned in arbitrary units
41 Learning a Sensor Model Assume accurate action model Plot x a (t) against beacon height in image Best fit polynomial is learned sensor model
42 Learning a Sensor Model Assume accurate action model Plot x a (t) against beacon height in image Best fit polynomial is learned sensor model x (t) a Walking Forwards Observations: Walking Backwards Observations: Best Fit Cubic (to all data): Beacon Height
43 Learning an Action Model Assume accurate sensor model Plot x s (t) against time
44 Learning an Action Model Assume accurate sensor model Plot x s (t) against time x (t) s Observations: Time (s)
45 Learning an Action Model Assume accurate sensor model Plot x s (t) against time x (t) s Observations: Time (s) Compute action model that minimizes the error Problem equivalent to another polynomial regression
46 Learning an Action Model Assume accurate sensor model is accurate Plot x s (t) against time x (t) s Observations: Learned Action Model: Time (s) Compute action model that minimizes the error Problem equivalent to another polynomial regression
47 Learning Both Simultaneously Both models improve via bootstrapping Maintain two notions of location, x s (t) and x a (t) Each used to fit the other model
48 Learning Both Simultaneously Both models improve via bootstrapping Maintain two notions of location, x s (t) and x a (t) Each used to fit the other model Use weighted regression w i = γ n i, γ < 1 Can still be computed incrementally
49 Learning Both Simultaneously Both models improve via bootstrapping Maintain two notions of location, x s (t) and x a (t) Each used to fit the other model Use weighted regression w i = γ n i, γ < 1 Can still be computed incrementally Ramping up St A 0 A t t = 0 t = t start t = 2t start
50 Learning Both Simultaneously Over 2.5 min., x s (t) and x a (t) converge x(t) Time (s)
51 Experimental Results Run ASAMI for pre-set amount of time (2.5 minutes) Measure actual models with stopwatch and ruler
52 Experimental Results Run ASAMI for pre-set amount of time (2.5 minutes) Measure actual models with stopwatch and ruler Compare measured vs. learned after best scaling
53 Experimental Results Run ASAMI for pre-set amount of time (2.5 minutes) Measure actual models with stopwatch and ruler Compare measured vs. learned after best scaling Vel. Dist. Measured Sensor Model: Learned Sensor Model: Measured Action Model: Learned Action Model: Action Command Beacon Height
54 Experimental Results Average fitness of model over 15 runs 200 Error (mm, mm/s) Learned Action Model Error Learned Sensor Model Error Time (s)
55 Summary ASAMI: Autonomous, no external feedback Computationally efficient Starts with poor action model, no sensor model Learns accurate approximations to both models Models are to scale with each other
56 Outline Learning sensor and action models [Stronger, S, 06] Machine learning for fast walking [Kohl, S, 04] Learning to acquire the ball [Fidelman, S, 06] Color constancy on mobile robots [Sridharan, S, 04] Autonomous Color Learning [Sridharan, S, 06]
57 Policy Gradient RL to learn fast walk Goal: Enable an Aibo to walk as fast as possible
58 Policy Gradient RL to learn fast walk Goal: Enable an Aibo to walk as fast as possible Start with a parameterized walk Learn fastest possible parameters
59 Policy Gradient RL to learn fast walk Goal: Enable an Aibo to walk as fast as possible Start with a parameterized walk Learn fastest possible parameters No simulator available: Learn entirely on robots Minimal human intervention
60 Walking Aibos Walks that come with Aibo are slow RoboCup soccer: 25+ Aibo teams internationally Motivates faster walks
61 Walking Aibos Walks that come with Aibo are slow RoboCup soccer: 25+ Aibo teams internationally Motivates faster walks Hand-tuned gaits [2003] Learned gaits German UT Austin Hornby et al. Kim & Uther Team Villa UNSW [1999] [2003] 230 mm/s (±5)
62 A Parameterized Walk Developed from scratch as part of UT Austin Villa 2003 Trot gait with elliptical locus on each leg
63 Locus Parameters z x y Ellipse length Ellipse height Position on x axis Position on y axis Body height Timing values 12 continuous parameters
64 Locus Parameters z x y Ellipse length Ellipse height Position on x axis Position on y axis Body height Timing values 12 continuous parameters Hand tuning by April, 03: 140 mm/s Hand tuning by July, 03: 245 mm/s
65 Experimental Setup Policy π = {θ 1,..., θ 12 }, V (π) = walk speed when using π
66 Experimental Setup Policy π = {θ 1,..., θ 12 }, V (π) = walk speed when using π Training Scenario Robots time themselves traversing fixed distance Multiple traversals (3) per policy to account for noise
67 Experimental Setup Policy π = {θ 1,..., θ 12 }, V (π) = walk speed when using π Training Scenario Robots time themselves traversing fixed distance Multiple traversals (3) per policy to account for noise Multiple robots evaluate policies simultaneously Off-board computer collects results, assigns policies
68 Experimental Setup Policy π = {θ 1,..., θ 12 }, V (π) = walk speed when using π Training Scenario Robots time themselves traversing fixed distance Multiple traversals (3) per policy to account for noise Multiple robots evaluate policies simultaneously Off-board computer collects results, assigns policies No human intervention except battery changes
69 Policy Gradient RL From π want to move in direction of gradient of V (π)
70 Policy Gradient RL From π want to move in direction of gradient of V (π) Can t compute V (π) θ i directly: estimate empirically
71 Policy Gradient RL From π want to move in direction of gradient of V (π) Can t compute V (π) θ i directly: estimate empirically Evaluate neighboring policies to estimate gradient Each trial randomly varies every parameter
72 Policy Gradient RL From π want to move in direction of gradient of V (π) Can t compute V (π) θ i directly: estimate empirically Evaluate neighboring policies to estimate gradient Each trial randomly varies every parameter
73 Experiments Started from stable, but fairly slow gait Used 3 robots simultaneously Each iteration takes 45 traversals, minutes
74 Experiments Started from stable, but fairly slow gait Used 3 robots simultaneously Each iteration takes 45 traversals, minutes Before learning After learning 24 iterations = 1080 field traversals, 3 hours
75 Results 300 Velocity of Learned Gait during Training Learned Gait (UT Austin Villa) 280 Velocity (mm/s) Learned Gait (UNSW) Hand tuned Gait (UNSW) Hand tuned Gait (UT Austin Villa) Hand tuned Gait (German Team) Number of Iterations
76 Results 300 Velocity of Learned Gait during Training Learned Gait (UT Austin Villa) 280 Velocity (mm/s) Learned Gait (UNSW) Hand tuned Gait (UNSW) Hand tuned Gait (UT Austin Villa) Hand tuned Gait (German Team) Number of Iterations Additional iterations didn t help Spikes: evaluation noise? large step size?
77 Learned Parameters Parameter Initial ɛ Best Value Value Front ellipse: (height) (x offset) (y offset) Rear ellipse: (height) (x offset) (y offset) Ellipse length Ellipse skew multiplier Front height Rear height Time to move through locus Time on ground
78 Algorithmic Comparison, Robot Port Before learning After learning
79 Summary Used policy gradient RL to learn fastest Aibo walk All learning done on real robots No human itervention (except battery changes)
80 Outline Learning sensor and action models [Stronger, S, 06] Machine learning for fast walking [Kohl, S, 04] Learning to acquire the ball [Fidelman, S, 06] Color constancy on mobile robots [Sridharan, S, 05] Autonomous Color Learning [Sridharan, S, 06]
81 Grasping the Ball Three stages: walk to ball; slow down; lower chin Head proprioception, IR chest sensor ball distance Movement specified by 4 parameters
82 Grasping the Ball Three stages: walk to ball; slow down; lower chin Head proprioception, IR chest sensor ball distance Movement specified by 4 parameters Brittle!
83 Parameterization slowdown dist: when to slow down slowdown factor: how much to slow down capture angle: when to stop turning capture dist: when to put down head
84 Learning the Chin Pinch Binary, noisy reinforcement signal: multiple trials Robot evaluates self: no human intervention
85 Results Evaluation of policy gradient, hill climbing, amoeba successful captures out of 100 trials policy gradient amoeba hill climbing iterations
86 What it learned Policy slowdown slowdown capture capture Success dist factor angle dist rate Initial 200mm o 110mm 36% Policy gradient 125mm o 152mm 64% Amoeba 208mm o 162mm 69% Hill climbing 240mm o 170mm 66%
87 Instance of Layered Learning For domains too complex for tractably mapping state features S outputs O
88 Instance of Layered Learning For domains too complex for tractably mapping state features S outputs O Hierarchical subtask decomposition given: {L 1, L 2,..., L n }
89 Instance of Layered Learning For domains too complex for tractably mapping state features S outputs O Hierarchical subtask decomposition given: {L 1, L 2,..., L n } Machine learning: exploit data to train, adapt
90 Instance of Layered Learning For domains too complex for tractably mapping state features S outputs O Hierarchical subtask decomposition given: {L 1, L 2,..., L n } Machine learning: exploit data to train, adapt Learning in one layer feeds into next layer
91 Instance of Layered Learning For domains too complex for tractably mapping state features S outputs O Hierarchical subtask decomposition given: {L 1, L 2,..., L n } Machine learning: exploit data to train, adapt Learning in one layer feeds into next layer High Level Goals Adversarial Behaviors Team Behaviors Multi-Agent Behaviors Machine Learning Opportunities Individual Behaviors World State Environment
92 Outline Learning sensor and action models [Stronger, S, 06] Machine learning for fast walking [Kohl, S, 04] Learning to acquire the ball [Fidelman, S, 06] Color constancy on mobile robots [Sridharan, S, 05] Autonomous Color Learning [Sridharan, S, 06]
MLSS 2015 Robot Learning
MLSS 2015 Robot Learning Prof: Department of Computer Science The University of Texas at Austin Applications: Robot Learning Lots of models/functions to learn from data Applications: Robot Learning Lots
More informationTowards Autonomous Sensor and Actuator Model Induction on a Mobile Robot
In Connection Science (Special Issue on Developmental Robotics), 18(2): 97-119, 2006. Towards Autonomous Sensor and Actuator Model Induction on a Mobile Robot Daniel Stronger Department of Computer Sciences
More informationMachine Learning for Fast Quadrupedal Locomotion
In The Nineteenth National Conference on Artificial Intelligence (AAAI 2004), pp. 611-616, San Francisco, CA, July 2004. Machine Learning for Fast Quadrupedal Locomotion Nate Kohl and Peter Stone Department
More informationInstance-Based Action Models for Fast Action Planning
In Visser, Ribeiro, Ohashi and Dellaert, editors, RoboCup-2007. Robot Soccer World Cup XI, pp. 1-16, Springer Verlag, 2008. Instance-Based Action Models for Fast Action Planning Mazda Ahmadi and Peter
More informationInstance-Based Action Models for Fast Action Planning
Instance-Based Action Models for Fast Action Planning Mazda Ahmadi and Peter Stone Department of Computer Sciences The University of Texas at Austin 1 University Station C0500, Austin, TX 78712-0233 Email:{mazda,pstone}@cs.utexas.edu
More informationontents 1 Introduction 4 2 General Architecture WorldState Vision amera Settings
The UT Austin Villa 2004 Roboup Four-Legged Team: oming of Age Peter Stone, Kurt Dresner, Peggy Fidelman, Nicholas K. Jong, Nate Kohl, Gregory Kuhlmann, Mohan Sridharan, Daniel Stronger Department of omputer
More informationRobotics. CSPP Artificial Intelligence March 10, 2004
Robotics CSPP 56553 Artificial Intelligence March 10, 2004 Roadmap Robotics is AI-complete Integration of many AI techniques Classic AI Search in configuration space (Ultra) Modern AI Subsumption architecture
More informationImproving Vision-Based Distance Measurements using Reference Objects
Improving Vision-Based Distance Measurements using Reference Objects Matthias Jüngel, Heinrich Mellmann, and Michael Spranger Humboldt-Universität zu Berlin, Künstliche Intelligenz Unter den Linden 6,
More informationSHARPKUNGFU TEAM DESCRIPTION 2006
SHARPKUNGFU TEAM DESCRIPTION 2006 Qining Wang, Chunxia Rong, Yan Huang, Guangming Xie, Long Wang Intelligent Control Laboratory, College of Engineering, Peking University, Beijing 100871, China http://www.mech.pku.edu.cn/robot/fourleg/
More informationRobotics. Haslum COMP3620/6320
Robotics P@trik Haslum COMP3620/6320 Introduction Robotics Industrial Automation * Repetitive manipulation tasks (assembly, etc). * Well-known, controlled environment. * High-power, high-precision, very
More informationA Model-Based Approach to Robot Joint Control
In Daniele Nardi, Martin Riedmiller, and Claude Sammut, editors, RoboCup-24, pp. 297-39, Springer Verlag, 25. A Model-Based Approach to Robot Joint Control Daniel Stronger and Peter Stone Department of
More informationA Neural Network-Based Approach to Robot Motion Control
In Visser, Ribeiro, Ohashi, and Dellaert, editors, RoboCup-2007, Springer Verlag, 2008. A Neural Network-Based Approach to Robot Motion Control Uli Grasemann, Daniel Stronger, and Peter Stone Department
More informationEagle Knights 2007: Four-Legged League
Eagle Knights 2007: Four-Legged League Alfredo Weitzenfeld 1, Alonso Martínez 1, Bernardo Muciño 1, Gabriela Serrano 1, Carlos Ramos 1, and Carlos Rivera 1 1 Robotics Laboratory Lab, ITAM, Rio Hondo 1,
More informationThe 2006 sharpkungfu Team Report
The 2006 sharpkungfu Team Report Qining Wang, Chunxia Rong, Lianghuan Liu, Hua Li, and Guangming Xie Intelligent Control Laboratory, Center for Systems and Control, College of Engineering, Peking University,
More informationContents 1 Introduction 5 2 The Class 5 3 Initial Behaviors 6 4 Vision Camera Settings Color Se
UT Austin Villa 2003: A New RoboCup Four-Legged Team Peter Stone, Kurt Dresner, Selim T. Erdo gan, Peggy Fidelman, Nicholas K. Jong, Nate Kohl, Gregory Kuhlmann, Ellie Lin, Mohan Sridharan, Daniel Stronger,
More informationParticle-Filter-Based Self-Localization Using Landmarks and Directed Lines
Particle-Filter-Based Self-Localization Using Landmarks and Directed Lines Thomas Röfer 1, Tim Laue 1, and Dirk Thomas 2 1 Center for Computing Technology (TZI), FB 3, Universität Bremen roefer@tzi.de,
More informationBabyTigers-98: Osaka Legged Robot Team
BabyTigers-98: saka Legged Robot Team Noriaki Mitsunaga and Minoru Asada and Chizuko Mishima Dept. of Adaptive Machine Systems, saka niversity, Suita, saka, 565-0871, Japan Abstract. The saka Legged Robot
More informationA Hybrid Software Platform for Sony AIBO Robots
A Hybrid Software Platform for Sony AIBO Robots Dragos Golubovic, Bo Li, Huosheng Hu Department of Computer Science, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, United Kingdom Email: {dgolub,
More informationPractical Extensions to Vision-Based Monte Carlo Localization Methods for Robot Soccer Domain
Practical Extensions to Vision-Based Monte Carlo Localization Methods for Robot Soccer Domain Kemal Kaplan 1, Buluç Çelik 1, Tekin Meriçli 2, Çetin Meriçli 1 and H. Levent Akın 1 1 Boğaziçi University
More informationJolly Pochie 2005 in the Four Legged Robot League
Jolly Pochie 2005 in the Four Legged Robot League Jun Inoue 1, Hayato Kobayashi 1, Akira Ishino 2, and Ayumi Shinohara 3 1 Department of Informatics, Kyushu University {j-inoue, h-koba}@i.kyushu-u.ac.jp
More informationVision-based Safe Local Motion on a Humanoid Robot
Vision-based Safe Local Motion on a Humanoid Robot Xiang Li Texas Tech University, USA xiang.li@ttu.edu Shiqi Zhang Texas Tech University, USA s.zhang@ttu.edu Mohan Sridharan Texas Tech University, USA
More informationNao Devils Dortmund. Team Description Paper for RoboCup Matthias Hofmann, Ingmar Schwarz, and Oliver Urbann
Nao Devils Dortmund Team Description Paper for RoboCup 2017 Matthias Hofmann, Ingmar Schwarz, and Oliver Urbann Robotics Research Institute Section Information Technology TU Dortmund University 44221 Dortmund,
More informationState Estimation for Continuous-Time Systems with Perspective Outputs from Discrete Noisy Time-Delayed Measurements
State Estimation for Continuous-Time Systems with Perspective Outputs from Discrete Noisy Time-Delayed Measurements António Pedro Aguiar aguiar@ece.ucsb.edu João Pedro Hespanha hespanha@ece.ucsb.edu Dept.
More information7-5 Parametric Equations
3. Sketch the curve given by each pair of parametric equations over the given interval. Make a table of values for 6 t 6. t x y 6 19 28 5 16.5 17 4 14 8 3 11.5 1 2 9 4 1 6.5 7 0 4 8 1 1.5 7 2 1 4 3 3.5
More informationThe University of Pennsylvania Robocup 2011 SPL Nao Soccer Team
The University of Pennsylvania Robocup 2011 SPL Nao Soccer Team General Robotics Automation, Sensing and Perception (GRASP) Laboratory University of Pennsylvania, Philadelphia, PA 19104 Abstract. This
More informationMarco Wiering Intelligent Systems Group Utrecht University
Reinforcement Learning for Robot Control Marco Wiering Intelligent Systems Group Utrecht University marco@cs.uu.nl 22-11-2004 Introduction Robots move in the physical environment to perform tasks The environment
More informationBall tracking with velocity based on Monte-Carlo localization
Book Title Book Editors IOS Press, 23 1 Ball tracking with velocity based on Monte-Carlo localization Jun Inoue a,1, Akira Ishino b and Ayumi Shinohara c a Department of Informatics, Kyushu University
More informationTrot Gait Design details for Quadrupeds
Trot Gait Design details for Quadrupeds Vincent Hugel, Pierre Blazevic, Olivier Stasse, and Patrick Bonnin Laboratoire de Robotique de Versailles (LRV), 10/12 avenue de l Europe, 78140 Vélizy, France hugel@robot.uvsq.fr
More informationVisual Attention Control by Sensor Space Segmentation for a Small Quadruped Robot based on Information Criterion
Visual Attention Control by Sensor Space Segmentation for a Small Quadruped Robot based on Information Criterion Noriaki Mitsunaga and Minoru Asada Dept. of Adaptive Machine Systems, Osaka University,
More informationWrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions
WrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions Aijun Bai, Xiaoping Chen, Patrick MacAlpine, Daniel Urieli, Samuel Barrett, and Peter Stone Department of Computer Science, University
More informationLearning to Kick the Ball Using Back to Reality
Learning to Kick the Ball Using Back to Reality Juan Cristóbal Zagal and Javier Ruiz-del-Solar Department of Electrical Engineering, Universidad de Chile, Av. Tupper 2007, 6513027 Santiago, Chile {jzagal,
More informationDetecting Motion in the Environment with a Moving Quadruped Robot
Detecting Motion in the Environment with a Moving Quadruped Robot Peggy Fidelman 1, Thayne Coffman 2 and Risto Miikkulainen 1 1 Department of Computer Sciences The University of Texas at Austin 2 Department
More informationPolynomial Regression with Automated Degree: A Function Approximator for Autonomous Agents
To appear in International Conference on Tools with Artificial Intelligence (ICTAI 06), Arlington, VA, November 2006. Polynomial Regression with Automated Degree: A Function Approximator for Autonomous
More informationMithras3D Team Description Paper 2014 Soccer Simulation 3D League
Mithras3D Team Description Paper 2014 Soccer Simulation 3D League Armita Sabeti Ashraf, Atieh Alsadat Moosavian, Fatemeh Gerami Gohar, Fatima Tafazzoli Shadpour, Romina Moradi, Sama Moayeri Farzanegan
More informationThe 2012 UT Austin Villa Code Release
To appear in Proceedings of the RoboCup International Symposium 2013 (RoboCup 2013), Eindhoven, Netherlands, July 2013. The 2012 UT Austin Villa Code Release Samuel Barrett, Katie Genter, Yuchen He, Todd
More informationExpectation-Based Vision for Precise Self-Localization on a Mobile Robot
In Cognitive Robotics: Papers From the AAAI Workshop (AAAI 06), pp. 167-174, Boston, July 2006. Expectation-Based Vision for Precise Self-Localization on a Mobile Robot Daniel Stronger and Peter Stone
More informationOn-line Robot Adaptation to Environmental Change
On-line Robot Adaptation to Environmental Change Scott Lenser CMU-CS-05-165 August, 2005 School of Computer Science Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee:
More informationGrasping Known Objects with Aldebaran Nao
CS365 Project Report Grasping Known Objects with Aldebaran Nao By: Ashu Gupta( ashug@iitk.ac.in) Mohd. Dawood( mdawood@iitk.ac.in) Department of Computer Science and Engineering IIT Kanpur Mentor: Prof.
More informationRobot Controller. Sensor Processing Module. Locomotion Module. Sensors. Environment
Evolution of Controllers from a High-Level Simulator to a High DOF Robot G. S. Hornby 1, S. Takamura 2, O. Hanagata 3, M. Fujita 3, and J. Pollack 1 1 Computer Science Dept., Brandeis University, Waltham,
More informationReal-Time Vision on a Mobile Robot Platform
In The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 05), Edmonton, Canada, August 2005. Real-Time Vision on a Mobile Robot Platform Mohan Sridharan Electrical and Computer
More informationAdaptive Field Detection and Localization in Robot Soccer
Adaptive Field Detection and Localization in Robot Soccer Yongbo Qian and Daniel D. Lee GRASP Lab, University of Pennsylvania, Philadelphia PA 19104, USA, {yongbo,ddlee}@seas.upenn.edu https://www.grasp.upenn.edu/
More informationBrainstormers Team Description
Brainstormers 2003 - Team Description M. Riedmiller, A. Merke, M. Nickschas, W. Nowak, and D. Withopf Lehrstuhl Informatik I, Universität Dortmund, 44221 Dortmund, Germany Abstract. The main interest behind
More informationbeestanbul RoboCup 3D Simulation League Team Description Paper 2011
beestanbul RoboCup 3D Simulation League Team Description Paper 2011 Shahriar Asta, Tuna Sonmez, Onuralp Ulusoy, Alper Alimoglu, Mustafa Ersen, Ozdemir Sozmen, and Sanem Sariel-Talay Artificial Intelligence
More informationQuadruped Robots and Legged Locomotion
Quadruped Robots and Legged Locomotion J. Zico Kolter Computer Science Department Stanford University Joint work with Pieter Abbeel, Andrew Ng Why legged robots? 1 Why Legged Robots? There is a need for
More informationDept. of Adaptive Machine Systems, Graduate School of Engineering Osaka University, Suita, Osaka , Japan
An Application of Vision-Based Learning for a Real Robot in RoboCup - A Goal Keeping Behavior for a Robot with an Omnidirectional Vision and an Embedded Servoing - Sho ji Suzuki 1, Tatsunori Kato 1, Hiroshi
More informationThis article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and
This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research and education use, including for instruction at the authors institution
More informationAutomatic Gait Optimization with Gaussian Process Regression
Automatic Gait Optimization with Gaussian Process Regression Daniel Lizotte, Tao Wang, Michael Bowling, Dale Schuurmans Department of Computing Science University of Alberta {dlizotte,trysi,bowling,dale}@cs.ualberta.ca
More informationToday MAPS AND MAPPING. Features. process of creating maps. More likely features are things that can be extracted from images:
MAPS AND MAPPING Features In the first class we said that navigation begins with what the robot can see. There are several forms this might take, but it will depend on: What sensors the robot has What
More informationCarnegie Mellon University
Actuators & Motion Instructors: Prof. Manuela Veloso & Dr. Paul E. Rybski TAs: Sonia Chernova & Nidhi Kalra 15-491, Fall 2004 http://www.andrew.cmu.edu/course/15-491 Computer Science Department Carnegie
More informationPlymouth Humanoids Team Description Paper for RoboCup 2013
Plymouth Humanoids Team Description Paper for RoboCup 2013 Arron Griffiths 1, Clare Simpson, Paul Eastham, Alex Smith, Guido Bugmann, Chenguang Yang, Peter Gibbons, and Phil F. Culverhouse Centre for Robotics
More informationWrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions
WrightEagle and UT Austin Villa: RoboCup 2011 Simulation League Champions Aijun Bai 1, Xiaoping Chen 1, Patrick MacAlpine 2,DanielUrieli 2, Samuel Barrett 2, and Peter Stone 2 1 Department of Computer
More informationBehavior Learning for a Mobile Robot with Omnidirectional Vision Enhanced by an Active Zoom Mechanism
Behavior Learning for a Mobile Robot with Omnidirectional Vision Enhanced by an Active Zoom Mechanism Sho ji Suzuki, Tatsunori Kato, Minoru Asada, and Koh Hosoda Dept. of Adaptive Machine Systems, Graduate
More informationMotion Control in Dynamic Multi-Robot Environments
Motion Control in Dynamic Multi-Robot Environments Michael Bowling mhb@cs.cmu.edu Manuela Veloso mmv@cs.cmu.edu Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213-3890 Abstract
More informationInverse KKT Motion Optimization: A Newton Method to Efficiently Extract Task Spaces and Cost Parameters from Demonstrations
Inverse KKT Motion Optimization: A Newton Method to Efficiently Extract Task Spaces and Cost Parameters from Demonstrations Peter Englert Machine Learning and Robotics Lab Universität Stuttgart Germany
More informationHorus: Object Orientation and Id without Additional Markers
Computer Science Department of The University of Auckland CITR at Tamaki Campus (http://www.citr.auckland.ac.nz) CITR-TR-74 November 2000 Horus: Object Orientation and Id without Additional Markers Jacky
More informationNao recognition and coordination
Nao recognition and coordination Sander Nugteren August 24, 2012 1 Project In RoboCup soccer, it is important to have robots communicate and position themselves properly. This prevents them from getting
More informationGenerality and Simple Hands
Generality and Simple Hands with Grasp Invariance Matthew T. Mason and Alberto Rodriguez February 18, 2011 Outline 1. Overview of Robotics Institute (Mason) 2. Simple hands project (Mason) 3. Grasp invariance
More informationTowards a methodology for stabilizing the gaze of a quadrupedal robot
Towards a methodology for stabilizing the gaze of a quadrupedal robot Marek Marcinkiewicz, Mikhail Kunin, Simon Parsons, Elizabeth Sklar, and Theodore Raphan Department of Computer & Information Science
More informationA Comparison of Two Approaches for Vision and Self-Localization on a Mobile Robot
2007 IEEE International Conference on Robotics and Automation Roma, Italy, 10-14 April 2007 FrC1.3 A Comparison of Two Approaches for Vision and Self-Localization on a Mobile Robot Daniel Stronger and
More informationSelective Visual Attention for Object Detection on a Legged Robot
In Gerhard Lakemeyer, Elizabeth Sklar, Domenico Sorenti, and Tomoichi Takahashi, editors, RoboCup-2006, Springer Verlag, 2007. Selective Visual Attention for Object Detection on a Legged Robot Daniel Stronger
More informationACE Project Report. December 10, Reid Simmons, Sanjiv Singh Robotics Institute Carnegie Mellon University
ACE Project Report December 10, 2007 Reid Simmons, Sanjiv Singh Robotics Institute Carnegie Mellon University 1. Introduction This report covers the period from September 20, 2007 through December 10,
More informationHierarchical Reinforcement Learning for Robot Navigation
Hierarchical Reinforcement Learning for Robot Navigation B. Bischoff 1, D. Nguyen-Tuong 1,I-H.Lee 1, F. Streichert 1 and A. Knoll 2 1- Robert Bosch GmbH - Corporate Research Robert-Bosch-Str. 2, 71701
More informationUsing Layered Color Precision for a Self-Calibrating Vision System
ROBOCUP2004 SYMPOSIUM, Instituto Superior Técnico, Lisboa, Portugal, July 4-5, 2004. Using Layered Color Precision for a Self-Calibrating Vision System Matthias Jüngel Institut für Informatik, LFG Künstliche
More informationIntroduction to Mobile Robotics
Introduction to Mobile Robotics Gaussian Processes Wolfram Burgard Cyrill Stachniss Giorgio Grisetti Maren Bennewitz Christian Plagemann SS08, University of Freiburg, Department for Computer Science Announcement
More informationIntroduction. Chapter Overview
Chapter 1 Introduction The Hough Transform is an algorithm presented by Paul Hough in 1962 for the detection of features of a particular shape like lines or circles in digitalized images. In its classical
More informationApplying the Episodic Natural Actor-Critic Architecture to Motor Primitive Learning
Applying the Episodic Natural Actor-Critic Architecture to Motor Primitive Learning Jan Peters 1, Stefan Schaal 1 University of Southern California, Los Angeles CA 90089, USA Abstract. In this paper, we
More informationAn Efficient Need-Based Vision System in Variable Illumination Environment of Middle Size RoboCup
An Efficient Need-Based Vision System in Variable Illumination Environment of Middle Size RoboCup Mansour Jamzad and Abolfazal Keighobadi Lamjiri Sharif University of Technology Department of Computer
More informationNuBot Team Description Paper 2013
NuBot Team Description Paper 2013 Zhiwen Zeng, Dan Xiong, Qinghua Yu, Kaihong Huang, Shuai Cheng, Huimin Lu, Xiangke Wang, Hui Zhang, Xun Li, Zhiqiang Zheng College of Mechatronics and Automation, National
More informationOptimization of a two-link Robotic Manipulator
Optimization of a two-link Robotic Manipulator Zachary Renwick, Yalım Yıldırım April 22, 2016 Abstract Although robots are used in many processes in research and industry, they are generally not customized
More informationEstimation of Planar Surfaces in Noisy Range Images for the RoboCup Rescue Competition
Estimation of Planar Surfaces in Noisy Range Images for the RoboCup Rescue Competition Johannes Pellenz pellenz@uni-koblenz.de with Sarah Steinmetz and Dietrich Paulus Working Group Active Vision University
More informationLocal Search Methods. CS 188: Artificial Intelligence Fall Announcements. Hill Climbing. Hill Climbing Diagram. Today
CS 188: Artificial Intelligence Fall 2006 Lecture 5: Robot Motion Planning 9/14/2006 Local Search Methods Queue-based algorithms keep fallback options (backtracking) Local search: improve what you have
More informationAcquiring a Robust Case Base for the Robot Soccer Domain
Acquiring a Robust Case Base for the Robot Soccer Domain Raquel Ros, Josep Lluís Arcos IIIA - Artificial Intelligence Research Institute CSIC - Spanish Council for Scientific Research Campus UAB, 08193
More informationSimplified Walking: A New Way to Generate Flexible Biped Patterns
1 Simplified Walking: A New Way to Generate Flexible Biped Patterns Jinsu Liu 1, Xiaoping Chen 1 and Manuela Veloso 2 1 Computer Science Department, University of Science and Technology of China, Hefei,
More informationTowards a Calibration-Free Robot: The ACT Algorithm for Automatic Online Color Training
Towards a Calibration-Free Robot: The ACT Algorithm for Automatic Online Color Training Patrick Heinemann, Frank Sehnke, Felix Streichert, and Andreas Zell Wilhelm-Schickard-Institute, Department of Computer
More informationUPennalizers. RoboCup Standard Platform League Team Report 2010
UPennalizers RoboCup Standard Platform League Team Report 2010 Jordan Brindza, Levi Cai, Ashleigh Thomas, Ross Boczar, Alyin Caliskan, Alexandra Lee, Anirudha Majumdar, Roman Shor, Barry Scharfman, Dan
More information10703 Deep Reinforcement Learning and Control
10703 Deep Reinforcement Learning and Control Russ Salakhutdinov Machine Learning Department rsalakhu@cs.cmu.edu Policy Gradient I Used Materials Disclaimer: Much of the material and slides for this lecture
More informationThomas Bräunl EMBEDDED ROBOTICS. Mobile Robot Design and Applications with Embedded Systems. Second Edition. With 233 Figures and 24 Tables.
Thomas Bräunl EMBEDDED ROBOTICS Mobile Robot Design and Applications with Embedded Systems Second Edition With 233 Figures and 24 Tables Springer CONTENTS PART I: EMBEDDED SYSTEMS 1 Robots and Controllers
More informationProblem characteristics. Dynamic Optimization. Examples. Policies vs. Trajectories. Planning using dynamic optimization. Dynamic Optimization Issues
Problem characteristics Planning using dynamic optimization Chris Atkeson 2004 Want optimal plan, not just feasible plan We will minimize a cost function C(execution). Some examples: C() = c T (x T ) +
More informationAdaptive Motion Control: Dynamic Kick for a Humanoid Robot
Adaptive Motion Control: Dynamic Kick for a Humanoid Robot Yuan Xu and Heinrich Mellmann Institut für Informatik, LFG Künstliche Intelligenz Humboldt-Universität zu Berlin, Germany {xu,mellmann}@informatik.hu-berlin.de
More informationCSE 490R P3 - Model Learning and MPPI Due date: Sunday, Feb 28-11:59 PM
CSE 490R P3 - Model Learning and MPPI Due date: Sunday, Feb 28-11:59 PM 1 Introduction In this homework, we revisit the concept of local control for robot navigation, as well as integrate our local controller
More informationTheory of Robotics and Mechatronics
Theory of Robotics and Mechatronics Final Exam 19.12.2016 Question: 1 2 3 Total Points: 18 32 10 60 Score: Name: Legi-Nr: Department: Semester: Duration: 120 min 1 A4-sheet (double sided) of notes allowed
More informationControl Approaches for Walking and Running
DLR.de Chart 1 > Humanoids 2015 > Christian Ott > 02.11.2015 Control Approaches for Walking and Running Christian Ott, Johannes Englsberger German Aerospace Center (DLR) DLR.de Chart 2 > Humanoids 2015
More informationFast and Robust Edge-Based Localization in the Sony Four-Legged Robot League
Fast and Robust Edge-Based Localization in the Sony Four-Legged Robot League Thomas Röfer 1 and Matthias Jüngel 2 1 Bremer Institut für Sichere Systeme, Technologie-Zentrum Informatik, FB 3, Universität
More informationThe NAO Robot, a case of study Robotics Franchi Alessio Mauro
The NAO Robot, a case of study Robotics 2013-2014 Franchi Alessio Mauro alessiomauro.franchi@polimi.it Who am I? Franchi Alessio Mauro Master Degree in Computer Science Engineer at Politecnico of Milan
More information08 An Introduction to Dense Continuous Robotic Mapping
NAVARCH/EECS 568, ROB 530 - Winter 2018 08 An Introduction to Dense Continuous Robotic Mapping Maani Ghaffari March 14, 2018 Previously: Occupancy Grid Maps Pose SLAM graph and its associated dense occupancy
More informationarxiv: v1 [cs.cv] 2 May 2016
16-811 Math Fundamentals for Robotics Comparison of Optimization Methods in Optical Flow Estimation Final Report, Fall 2015 arxiv:1605.00572v1 [cs.cv] 2 May 2016 Contents Noranart Vesdapunt Master of Computer
More informationModeling and kinematics simulation of freestyle skiing robot
Acta Technica 62 No. 3A/2017, 321 334 c 2017 Institute of Thermomechanics CAS, v.v.i. Modeling and kinematics simulation of freestyle skiing robot Xiaohua Wu 1,3, Jian Yi 2 Abstract. Freestyle skiing robot
More informationData Mining Practical Machine Learning Tools and Techniques. Slides for Chapter 6 of Data Mining by I. H. Witten and E. Frank
Data Mining Practical Machine Learning Tools and Techniques Slides for Chapter 6 of Data Mining by I. H. Witten and E. Frank Implementation: Real machine learning schemes Decision trees Classification
More informationA Fuzzy Reinforcement Learning for a Ball Interception Problem
A Fuzzy Reinforcement Learning for a Ball Interception Problem Tomoharu Nakashima, Masayo Udo, and Hisao Ishibuchi Department of Industrial Engineering, Osaka Prefecture University Gakuen-cho 1-1, Sakai,
More informationRobot Mapping. TORO Gradient Descent for SLAM. Cyrill Stachniss
Robot Mapping TORO Gradient Descent for SLAM Cyrill Stachniss 1 Stochastic Gradient Descent Minimize the error individually for each constraint (decomposition of the problem into sub-problems) Solve one
More informationStrategies for simulating pedestrian navigation with multiple reinforcement learning agents
Strategies for simulating pedestrian navigation with multiple reinforcement learning agents Francisco Martinez-Gil, Miguel Lozano, Fernando Ferna ndez Presented by: Daniel Geschwender 9/29/2016 1 Overview
More informationShip Patrol: Multiagent Patrol under Complex Environmental Conditions. Noa Agmon, Daniel Urieli and Peter Stone The University of Texas at Austin
Ship Patrol: Multiagent Patrol under Complex Environmental Conditions Noa Agmon, Daniel Urieli and Peter Stone The University of Texas at Austin Ship Patrol How It All Began Outline o Multiagent patrol
More informationLocally Weighted Learning for Control. Alexander Skoglund Machine Learning Course AASS, June 2005
Locally Weighted Learning for Control Alexander Skoglund Machine Learning Course AASS, June 2005 Outline Locally Weighted Learning, Christopher G. Atkeson et. al. in Artificial Intelligence Review, 11:11-73,1997
More informationReal-Time Vision on a Mobile Robot Platform
Real-Time Vision on a Mobile Robot Platform Mohan Sridharan and Peter Stone Department of Computer Sciences The University of Texas at Austin Austin, TX, 78731 Under review - not for citation Abstract
More informationCSE 490R P1 - Localization using Particle Filters Due date: Sun, Jan 28-11:59 PM
CSE 490R P1 - Localization using Particle Filters Due date: Sun, Jan 28-11:59 PM 1 Introduction In this assignment you will implement a particle filter to localize your car within a known map. This will
More informationKouretes 2008 Team Description Paper Nao Standard Platform League
Kouretes 2008 Team Description Paper Nao Standard Platform League Team Kouretes Technical University of Crete (TUC), Chania 73100, Crete, Greece Abstract. Kouretes is one of the 16 teams participating
More informationPersonal Computing ENIAC Apple II. Research Novelty tech Pervasive tools
Decision:!(s)! a 2 Personal Computing ENIAC Apple II Laptop OLPC Research Novelty tech Pervasive tools 3 Personal Computing ENIAC Apple II Laptop OLPC Internet ARPAnet Mosaic Gmail YouTube Graphics Sketchpad
More informationBONE CONTROLLER ASSET VERSION 0.1 REV 1
Foreword Thank you for purchasing the Bone Controller! I m an independent developer and your feedback and support really means a lot to me. Please don t ever hesitate to contact me if you have a question,
More informationLast update: May 6, Robotics. CMSC 421: Chapter 25. CMSC 421: Chapter 25 1
Last update: May 6, 2010 Robotics CMSC 421: Chapter 25 CMSC 421: Chapter 25 1 A machine to perform tasks What is a robot? Some level of autonomy and flexibility, in some type of environment Sensory-motor
More informationAn Interactive Software Environment for Gait Generation and Control Design of Sony Legged Robots
An Interactive Software Environment for Gait Generation and Control Design of Sony Legged Robots Dragos Golubovic and Huosheng Hu Department of Computer Science, University of Essex, Colchester CO4 3SQ,
More information