Func%on Approxima%on. Pieter Abbeel UC Berkeley EECS
|
|
- Philip McGee
- 6 years ago
- Views:
Transcription
1 Func%on Approxima%on Pieter Abbeel UC Berkeley EECS
2 Value Itera4on Algorithm: Start with for all s. For i=1,, H For all states s 2 S: Imprac4cal for large state spaces = the expected sum of rewards accumulated when star4ng from state s and ac4ng op4mally for a horizon of i steps = the op4mal ac4on when in state s and gemng to act for a horizon of i steps
3 Example: tetris state: board configura4on + shape of the falling piece ~2 200 states! ac4on: rota4on and transla4on applied to the falling piece 22 features aka basis func4ons Á i Ten basis func4ons, 0,..., 9, mapping the state to the height h[k] of each of the ten columns. Nine basis func4ons, 10,..., 18, each mapping the state to the absolute difference between heights of successive columns: h[k+1] h[k], k = 1,..., 9. One basis func4on, 19, that maps state to the maximum column height: max k h[k] One basis func4on, 20, that maps state to the number of holes in the board. One basis func4on, 21, that is equal to 1 in every state. ˆV θ (s) = 21 i=0 θ i φ i (s) =θ φ(s) [Bertsekas & Ioffe, 1996 (TD); Bertsekas & Tsitsiklis 1996 (TD); Kakade 2002 (policy gradient); Farias & Van Roy, 2006 (approximate LP)]
4 Function Approximation V(s) = + distance to closest ghost + θ 2 distance to closest power pellet + θ 3 in dead-end + θ 4 closer to power pellet than ghost is + = θ 0 θ 1 n θ i φ i (s) =θ φ(s) i=0
5 Func4on Approxima4on 0 th order approxima4on (1- nearest neighbor):. s x1 x2 x3 x x5 x6 x7 x8.... x9 x10 x11 x12 φ(s) = ˆV (s) = ˆV (x4) = θ 4 ˆV (s) =θ φ(s) Only store values for x1, x2,, x12 call these values θ 1, θ 2,...,θ 12 Assign other states value of nearest x state
6 Function Approximation 1 th order approxima4on (k- nearest neighbor interpola4on): ˆV (s) =φ 1 (s)θ 1 + φ 2 (s)θ 2 + φ 5 (s)θ 5 + φ 6 (s)θ x1. x2 x3 x4 s.... x5 x6 x7 x8.... x9 x10 x11 x12 φ(s) = ˆV (s) =θ φ(s) Only store values for x1, x2,, x12 call these values θ 1, θ 2,...,θ 12 Assign other states interpolated value of nearest 4 x states
7 Func4on Approxima4on Examples: S = R, ˆV (s) =θ1 + θ 2 s S = R, ˆV (s) =θ1 + θ 2 s + θ 3 s 2 S = R, ˆV (s) = n i=0 θ i s i S, ˆV (s) = log( exp(θ φ(s)) )
8 Func4on Approxima4on Main idea: ˆV θ Use approxima4on of the true value func4on, V θ is a free parameter to be chosen from its domain Θ S Representa4on size: à downto: Θ + : less parameters to es4mate - : less expressiveness, typically there exist many V for which there is no θ such that ˆVθ = V
9 Supervised Learning Given: set of examples (s (1),V(s (1) ), (s (2),V(s (2) ),...,(s (m),v(s (m) ) Asked for: best ˆV θ Representa4ve approach: find through least squares: min θ Θ m ( ˆV θ (s (i) ) V (s (i) )) 2 i=1 θ
10 Supervised Learning Example Linear regression Observa4on Error or residual Predic4on min θ 0,θ 1 n (θ 0 + θ 1 x (i) y (i) ) 2 i=
11 OverfiMng To avoid overfimng: reduce number of features used Prac4cal approach: leave- out valida4on Perform fimng for different choices of feature sets using just 70% of the data Pick feature set that led to highest quality of fit on the remaining 30% of data
12 Value Itera4on with Func4on Approxima4on Pick some (typically ) Ini4alize by choosing some semng for Iterate for i = 0, 1, 2,, H: Step 1: Bellman back- ups s S : S S Vi+1 (s) max a s T (s, a, s ) S << S θ (0) R(s, a, s )+γ ˆV θ (i)(s ) Step 2: Supervised learning find θ (i+1) as the solu4on of: min ˆVθ (i+1)(s) V 2 i+1 (s) θ s S
13 Infinite Horizon Linear Program min V µ 0 (s)v (s) s S s.t. V(s) s T (s, a, s )[R(s, a, s )+γv (s )], s S, a A µ 0 is a probability distribu4on over S, with µ 0 (s)> 0 for all s 2 S. Theorem. V * is the solu4on to the above LP.
14 Infinite Horizon Linear Program min V µ 0 (s)v (s) s S s.t. V(s) s T (s, a, s )[R(s, a, s )+γv (s )], s S, a A V (s) =θ φ(s) Let:, and consider S rather than S: min θ s S µ 0 (s)θ φ(s) s.t. θ φ(s) s T (s, a, s ) R(s, a, s )+γθ φ(s ), s S,a A à Linear program that finds ˆV θ (s) =θ φ(s)
15 Approximate Linear Program Guarantees** min θ s S µ 0 (s)θ φ(s) s.t. θ φ(s) s T (s, a, s ) R(s, a, s )+γθ φ(s ), s S,a A LP solver will converge Solu4on quality: [de Farias and Van Roy, 2002] Assuming one of the features is the feature that is equal to one for all states, and assuming S =S we have that: V Φθ 1,µ0 2 1 γ min V Φθ θ (slightly weaker, probabilis4c guarantees hold for S not equal to S, these guarantees require size of S to grow as the number of features grows)
16 Sampling-Based Motion Planning Pieter Abbeel UC Berkeley EECS Many images from Lavalle, Planning Algorithms
17 Motion Planning Problem Given start state x S, goal state x G Asked for: a sequence of control inputs that leads from start to goal Why tricky? Need to avoid obstacles For systems with underactuated dynamics: can t simply move along any coordinate at will E.g., car, helicopter, airplane, but also robot manipulator hitting joint limits
18 Solve by Nonlinear Optimization for Control? Could try by, for example, following formulation: X t can encode obstacles Or, with constraints, (which would require using an infeasible method): Can work surprisingly well, but for more complicated problems with longer horizons, often get stuck in local maxima that don t reach the goal
19 Examples Helicopter path planning Swinging up cart-pole Acrobot
20 Examples
21 Examples
22 Examples
23 Motion Planning: Outline Configuration Space Probabilistic Roadmap Boundary Value Problem Sampling Collision checking Rapidly-exploring Random Trees (RRTs) Smoothing
24 Configuration Space (C-Space) = { x x is a pose of the robot} obstacles à configuration space obstacles Workspace Configuration Space (2 DOF: translation only, no rotation) free space obstacles
25 Motion planning
26 Probabilistic Roadmap (PRM) Space R n forbidden space Free/feasible space 11
27 Probabilistic Roadmap (PRM) Configurations are sampled by picking coordinates at random 12
28 Probabilistic Roadmap (PRM) Configurations are sampled by picking coordinates at random 13
29 Probabilistic Roadmap (PRM) Sampled configurations are tested for collision 14
30 Probabilistic Roadmap (PRM) The collision-free configurations are retained as milestones 15
31 Probabilistic Roadmap (PRM) Each milestone is linked by straight paths to its nearest neighbors 16
32 Probabilistic Roadmap (PRM) Each milestone is linked by straight paths to its nearest neighbors 17
33 Probabilistic Roadmap (PRM) The collision-free links are retained as local paths to form the PRM 18
34 Probabilistic Roadmap (PRM) The start and goal configurations are included as milestones s g 19
35 Probabilistic Roadmap (PRM) The PRM is searched for a path from s to g s g 20
36 Probabilistic Roadmap Initialize set of points with x S and x G Randomly sample points in configuration space Connect nearby points if they can be reached from each other Find path from x S to x G in the graph Alternatively: keep track of connected components incrementally, and declare success when x S and x G are in same connected component
37 PRM example
38 PRM example 2
39 Sampling How to sample uniformly at random from [0,1] n? Sample uniformly at random from [0,1] for each coordinate How to sample uniformly at random from the surface of the n-d unit sphere? Sample from n-d Gaussian à isotropic; then just normalize How to sample uniformly at random for orientations in 3-D?
40 PRM: Challenges 1. Connecting neighboring points: Only easy for holonomic systems (i.e., for which you can move each degree of freedom at will at any time). Generally requires solving a Boundary Value Problem Typically solved without collision checking; later verified if valid by collision checking 2. Collision checking: Often takes majority of time in applications (see Lavalle)
41 PRM s Pros and Cons Pro: Probabilistically complete: i.e., with probability one, if run for long enough the graph will contain a solution path if one exists. Cons: Required to solve 2 point boundary value problem Build graph over state space but no particular focus on generating a path
42 Rapidly exploring Random Trees Basic idea: Build up a tree through generating next states in the tree by executing random controls However: not exactly above to ensure good coverage
43 Rapidly-exploring Random Trees (RRT) RANDOM_STATE(): often uniformly at random over space with probability 99%, and the goal state with probability 1%, this ensures it attempts to connect to goal semi-regularly
44 RRT Practicalities NEAREST_NEIGHBOR(x rand, T): need to find (approximate) nearest neighbor efficiently KD Trees data structure (upto 20-D) [e.g., FLANN] Locality Sensitive Hashing SELECT_INPUT(x rand, x near ) Two point boundary value problem If too hard to solve, often just select best out of a set of control sequences. This set could be random, or some well chosen set of primitives.
45 RRT Extension No obstacles, holonomic: With obstacles, holonomic: Non-holonomic: approximately (sometimes as approximate as picking best of a few random control sequences) solve two-point boundary value problem
46 Growing RRT Demo:
47 Bi-directional RRT Volume swept out by unidirectional RRT: x S x G Volume swept out by bi-directional RRT: x S x G Difference becomes far more pronounced in higher dimensions
48 Multi-directional RRT Planning around obstacles or through narrow passages can often be easier in one direction than the other
49 Resolution-Complete RRT (RC-RRT) Issue: nearest points chosen for expansion are (too) often the ones stuck behind an obstacle RC-RRT solution: Choose a maximum number of times, m, you are willing to try to expand each node For each node in the tree, keep track of its Constraint Violation Frequency (CVF) Initialize CVF to zero when node is added to tree Whenever an expansion from the node is unsuccessful (e.g., per hitting an obstacle): Increase CVF of that node by 1 Increase CVF of its parent node by 1/m, its grandparent 1/m 2, When a node is selected for expansion, skip over it with probability CVF/m
50 RRT* Source: Karaman and Frazzoli
51 RRT* Asymptotically optimal Main idea: Swap new point in as parent for nearby vertices who can be reached along shorter path through new point than through their original (current) parent
52 RRT* RRT RRT* Source: Karaman and Frazzoli
53 RRT* RRT RRT* Source: Karaman and Frazzoli
54 LQR-trees (Tedrake, IJRR 2010) Idea: grow a randomized tree of stabilizing controllers to the goal Like RRT Can discard sample points in already stabilized region
55 LQR-trees (Tedrake) Ck: stabilized region after iteration k
56 LQR-trees (Tedrake)
57 Smoothing Randomized motion planners tend to find not so great paths for execution: very jagged, often much longer than necessary. à In practice: do smoothing before using the path Shortcutting: along the found path, pick two vertices x t1, x t2 and try to connect them directly (skipping over all intermediate vertices) Nonlinear optimization for optimal control Allows to specify an objective function that includes smoothness in state, control, small control inputs, etc.
Sampling-Based Motion Planning
Sampling-Based Motion Planning Pieter Abbeel UC Berkeley EECS Many images from Lavalle, Planning Algorithms Motion Planning Problem Given start state x S, goal state x G Asked for: a sequence of control
More informationFunction Approximation. Pieter Abbeel UC Berkeley EECS
Function Approximation Pieter Abbeel UC Berkeley EECS Outline Value iteration with function approximation Linear programming with function approximation Value Iteration Algorithm: Start with for all s.
More informationCS 687 Jana Kosecka. Reinforcement Learning Continuous State MDP s Value Function approximation
CS 687 Jana Kosecka Reinforcement Learning Continuous State MDP s Value Function approximation Markov Decision Process - Review Formal definition 4-tuple (S, A, T, R) Set of states S - finite Set of actions
More informationPlanning & Decision-making in Robotics Planning Representations/Search Algorithms: RRT, RRT-Connect, RRT*
16-782 Planning & Decision-making in Robotics Planning Representations/Search Algorithms: RRT, RRT-Connect, RRT* Maxim Likhachev Robotics Institute Carnegie Mellon University Probabilistic Roadmaps (PRMs)
More informationSampling-based Planning 2
RBE MOTION PLANNING Sampling-based Planning 2 Jane Li Assistant Professor Mechanical Engineering & Robotics Engineering http://users.wpi.edu/~zli11 Problem with KD-tree RBE MOTION PLANNING Curse of dimension
More information6.141: Robotics systems and science Lecture 9: Configuration Space and Motion Planning
6.141: Robotics systems and science Lecture 9: Configuration Space and Motion Planning Lecture Notes Prepared by Daniela Rus EECS/MIT Spring 2012 Figures by Nancy Amato, Rodney Brooks, Vijay Kumar Reading:
More informationRobot Motion Planning
Robot Motion Planning James Bruce Computer Science Department Carnegie Mellon University April 7, 2004 Agent Planning An agent is a situated entity which can choose and execute actions within in an environment.
More informationTD(0) with linear function approximation guarantees
CS 287: Advanced Robotics Fall 2009 Lecture 15: LSTD, LSPI, RLSTD, imitation learning Pieter Abbeel UC Berkeley EECS TD(0) with linear function approximation guarantees Stochastic approximation of the
More informationLecture Schedule Week Date Lecture (W: 3:05p-4:50, 7-222)
2017 School of Information Technology and Electrical Engineering at the University of Queensland Lecture Schedule Week Date Lecture (W: 3:05p-4:50, 7-222) 1 26-Jul Introduction + 2 2-Aug Representing Position
More informationConfiguration Space of a Robot
Robot Path Planning Overview: 1. Visibility Graphs 2. Voronoi Graphs 3. Potential Fields 4. Sampling-Based Planners PRM: Probabilistic Roadmap Methods RRTs: Rapidly-exploring Random Trees Configuration
More informationCS 4649/7649 Robot Intelligence: Planning
CS 4649/7649 Robot Intelligence: Planning Probabilistic Roadmaps Sungmoon Joo School of Interactive Computing College of Computing Georgia Institute of Technology S. Joo (sungmoon.joo@cc.gatech.edu) 1
More informationAlgorithms for Sensor-Based Robotics: Sampling-Based Motion Planning
Algorithms for Sensor-Based Robotics: Sampling-Based Motion Planning Computer Science 336 http://www.cs.jhu.edu/~hager/teaching/cs336 Professor Hager http://www.cs.jhu.edu/~hager Recall Earlier Methods
More informationGeometric Path Planning McGill COMP 765 Oct 12 th, 2017
Geometric Path Planning McGill COMP 765 Oct 12 th, 2017 The Motion Planning Problem Intuition: Find a safe path/trajectory from start to goal More precisely: A path is a series of robot configurations
More informationLSTD(0) in policy iteration LSTD(0) Page 1. TD(0) with linear function approximation guarantees. TD(0) with linear function approximation guarantees
TD(0) with linear function approximation guarantees Stochastic approximation of the following operations: Back-up: (T π V)(s)= s T(s,π(s),s )[R(s,π(s),s )+γv(s )] CS 287: Advanced Robotics Fall 2009 Lecture
More informationManipula0on Algorithms Mo0on Planning. Mo#on Planning I. Katharina Muelling (NREC, Carnegie Mellon University) 1
16-843 Manipula0on Algorithms Mo0on Planning Mo#on Planning I Katharina Muelling (NREC, Carnegie Mellon University) 1 Configura0on Space Obstacles Star Algorithm Convex robot, transla#on C obs : convex
More informationAlgorithms for Sensor-Based Robotics: Sampling-Based Motion Planning
Algorithms for Sensor-Based Robotics: Sampling-Based Motion Planning Computer Science 336 http://www.cs.jhu.edu/~hager/teaching/cs336 Professor Hager http://www.cs.jhu.edu/~hager Recall Earlier Methods
More information6.141: Robotics systems and science Lecture 9: Configuration Space and Motion Planning
6.141: Robotics systems and science Lecture 9: Configuration Space and Motion Planning Lecture Notes Prepared by Daniela Rus EECS/MIT Spring 2011 Figures by Nancy Amato, Rodney Brooks, Vijay Kumar Reading:
More informationMotion Planning for Robot Manipulators
Motion Planning for Robot Manipulators Manuel Bonilla PhD Student manuel.bonilla@centropiaggio.unipi.it 26/05/15 http://manuel-bonilla.com 1 1. What is the interesting part of Motion planning in Robotics
More informationHumanoid Robotics. Inverse Kinematics and Whole-Body Motion Planning. Maren Bennewitz
Humanoid Robotics Inverse Kinematics and Whole-Body Motion Planning Maren Bennewitz 1 Motivation Planning for object manipulation Whole-body motion to reach a desired goal configuration Generate a sequence
More informationProbabilistic Methods for Kinodynamic Path Planning
16.412/6.834J Cognitive Robotics February 7 th, 2005 Probabilistic Methods for Kinodynamic Path Planning Based on Past Student Lectures by: Paul Elliott, Aisha Walcott, Nathan Ickes and Stanislav Funiak
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 informationNon-holonomic Planning
Non-holonomic Planning Jane Li Assistant Professor Mechanical Engineering & Robotics Engineering http://users.wpi.edu/~zli11 Recap We have learned about RRTs. q new q init q near q rand But the standard
More informationLQR-RRT : Optimal Sampling-Based Motion Planning with Automatically Derived Extension Heuristics
LQR-RRT : Optimal Sampling-Based Motion Planning with Automatically Derived Extension Heuristics Alejandro Perez, Robert Platt Jr., George Konidaris, Leslie Kaelbling and Tomas Lozano-Perez Computer Science
More informationAnnouncements. CS 188: Artificial Intelligence Fall Robot motion planning! Today. Robotics Tasks. Mobile Robots
CS 188: Artificial Intelligence Fall 2007 Lecture 6: Robot Motion Planning 9/13/2007 Announcements Project 1 due (yesterday)! Project 2 (Pacman with ghosts) up in a few days Reminder: you are allowed to
More informationCS 188: Artificial Intelligence Fall Announcements
CS 188: Artificial Intelligence Fall 2007 Lecture 6: Robot Motion Planning 9/13/2007 Dan Klein UC Berkeley Many slides over the course adapted from either Stuart Russell or Andrew Moore Announcements Project
More informationTrajectory Optimization
Trajectory Optimization Jane Li Assistant Professor Mechanical Engineering & Robotics Engineering http://users.wpi.edu/~zli11 Recap We heard about RRT*, a sampling-based planning in high-dimensional cost
More informationHumanoid Robotics. Inverse Kinematics and Whole-Body Motion Planning. Maren Bennewitz
Humanoid Robotics Inverse Kinematics and Whole-Body Motion Planning Maren Bennewitz 1 Motivation Plan a sequence of configurations (vector of joint angle values) that let the robot move from its current
More informationFinal Report: Dynamic Dubins-curve based RRT Motion Planning for Differential Constrain Robot
Final Report: Dynamic Dubins-curve based RRT Motion Planning for Differential Constrain Robot Abstract This project develops a sample-based motion-planning algorithm for robot with differential constraints.
More informationProbabilistic Motion Planning: Algorithms and Applications
Probabilistic Motion Planning: Algorithms and Applications Jyh-Ming Lien Department of Computer Science George Mason University Motion Planning in continuous spaces (Basic) Motion Planning (in a nutshell):
More informationRobotics Tasks. CS 188: Artificial Intelligence Spring Manipulator Robots. Mobile Robots. Degrees of Freedom. Sensors and Effectors
CS 188: Artificial Intelligence Spring 2006 Lecture 5: Robot Motion Planning 1/31/2006 Dan Klein UC Berkeley Many slides from either Stuart Russell or Andrew Moore Motion planning (today) How to move from
More informationDiscre'za'on. Pieter Abbeel UC Berkeley EECS
Discre'za'on Pieter Abbeel UC Berkeley EECS Markov Decision Process AssumpCon: agent gets to observe the state [Drawing from Su;on and Barto, Reinforcement Learning: An IntroducCon, 1998] Markov Decision
More informationScan Matching. Pieter Abbeel UC Berkeley EECS. Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics
Scan Matching Pieter Abbeel UC Berkeley EECS Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics Scan Matching Overview Problem statement: Given a scan and a map, or a scan and a scan,
More informationCS Path Planning
Why Path Planning? CS 603 - Path Planning Roderic A. Grupen 4/13/15 Robotics 1 4/13/15 Robotics 2 Why Motion Planning? Origins of Motion Planning Virtual Prototyping! Character Animation! Structural Molecular
More informationPart I Part 1 Sampling-based Motion Planning
Overview of the Lecture Randomized Sampling-based Motion Planning Methods Jan Faigl Department of Computer Science Faculty of Electrical Engineering Czech Technical University in Prague Lecture 05 B4M36UIR
More informationSampling-Based Robot Motion Planning. Lydia Kavraki Department of Computer Science Rice University Houston, TX USA
Sampling-Based Robot Motion Planning Lydia Kavraki Department of Computer Science Rice University Houston, TX USA Motion planning: classical setting Go from Start to Goal without collisions and while respecting
More informationPart I Part 1 Sampling-based Motion Planning
Overview of the Lecture Randomized Sampling-based Motion Planning Methods Jan Faigl Department of Computer Science Faculty of Electrical Engineering Czech Technical University in Prague Lecture 06 B4M36UIR
More informationVisual Navigation for Flying Robots. Motion Planning
Computer Vision Group Prof. Daniel Cremers Visual Navigation for Flying Robots Motion Planning Dr. Jürgen Sturm Motivation: Flying Through Forests 3 1 2 Visual Navigation for Flying Robots 2 Motion Planning
More informationRobot Motion Planning
Robot Motion Planning slides by Jan Faigl Department of Computer Science and Engineering Faculty of Electrical Engineering, Czech Technical University in Prague lecture A4M36PAH - Planning and Games Dpt.
More information6.141: Robotics systems and science Lecture 10: Implementing Motion Planning
6.141: Robotics systems and science Lecture 10: Implementing Motion Planning Lecture Notes Prepared by N. Roy and D. Rus EECS/MIT Spring 2011 Reading: Chapter 3, and Craig: Robotics http://courses.csail.mit.edu/6.141/!
More informationIntroduction to State-of-the-art Motion Planning Algorithms. Presented by Konstantinos Tsianos
Introduction to State-of-the-art Motion Planning Algorithms Presented by Konstantinos Tsianos Robots need to move! Motion Robot motion must be continuous Geometric constraints Dynamic constraints Safety
More informationPlanning and Control: Markov Decision Processes
CSE-571 AI-based Mobile Robotics Planning and Control: Markov Decision Processes Planning Static vs. Dynamic Predictable vs. Unpredictable Fully vs. Partially Observable Perfect vs. Noisy Environment What
More informationMotion Planning: Probabilistic Roadmaps. Corso di Robotica Prof. Davide Brugali Università degli Studi di Bergamo
Motion Planning: Probabilistic Roadmaps Corso di Robotica Prof. Davide Brugali Università degli Studi di Bergamo Tratto dalla lezione: Basic Motion Planning for a Point Robot CS 326A: Motion Planning ai.stanford.edu/~latombe/cs326/2007/index.htm
More informationAdvanced Robotics Path Planning & Navigation
Advanced Robotics Path Planning & Navigation 1 Agenda Motivation Basic Definitions Configuration Space Global Planning Local Planning Obstacle Avoidance ROS Navigation Stack 2 Literature Choset, Lynch,
More informationMotion Planning. COMP3431 Robot Software Architectures
Motion Planning COMP3431 Robot Software Architectures Motion Planning Task Planner can tell the robot discrete steps but can t say how to execute them Discrete actions must be turned into operations in
More informationII. RELATED WORK. A. Probabilistic roadmap path planner
Gaussian PRM Samplers for Dynamic Configuration Spaces Yu-Te Lin and Shih-Chia Cheng Computer Science Department Stanford University Stanford, CA 94305, USA {yutelin, sccheng}@cs.stanford.edu SUID: 05371954,
More informationUniversity of Nevada, Reno. Dynamic Path Planning and Replanning for Mobile Robot Team Using RRT*
University of Nevada, Reno Dynamic Path Planning and Replanning for Mobile Robot Team Using RRT* A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer
More informationMotion Planning for Humanoid Robots
Motion Planning for Humanoid Robots Presented by: Li Yunzhen What is Humanoid Robots & its balance constraints? Human-like Robots A configuration q is statically-stable if the projection of mass center
More informationECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space
ECE276B: Planning & Learning in Robotics Lecture 5: Configuration Space Lecturer: Nikolay Atanasov: natanasov@ucsd.edu Teaching Assistants: Tianyu Wang: tiw161@eng.ucsd.edu Yongxi Lu: yol070@eng.ucsd.edu
More informationRobot Motion Control Matteo Matteucci
Robot Motion Control Open loop control A mobile robot is meant to move from one place to another Pre-compute a smooth trajectory based on motion segments (e.g., line and circle segments) from start to
More informationChapter 12. Path Planning. Beard & McLain, Small Unmanned Aircraft, Princeton University Press, 2012,
Chapter 12 Path Planning Beard & McLain, Small Unmanned Aircraft, Princeton University Press, 212, Chapter 12: Slide 1 Control Architecture destination, obstacles map path planner waypoints status path
More informationApproximate path planning. Computational Geometry csci3250 Laura Toma Bowdoin College
Approximate path planning Computational Geometry csci3250 Laura Toma Bowdoin College Outline Path planning Combinatorial Approximate Combinatorial path planning Idea: Compute free C-space combinatorially
More information6.141: Robotics systems and science Lecture 10: Motion Planning III
6.141: Robotics systems and science Lecture 10: Motion Planning III Lecture Notes Prepared by N. Roy and D. Rus EECS/MIT Spring 2012 Reading: Chapter 3, and Craig: Robotics http://courses.csail.mit.edu/6.141/!
More informationcrrt : Planning loosely-coupled motions for multiple mobile robots
crrt : Planning loosely-coupled motions for multiple mobile robots Jan Rosell and Raúl Suárez Institute of Industrial and Control Engineering (IOC) Universitat Politècnica de Catalunya (UPC) Barcelona
More informationfor Motion Planning RSS Lecture 10 Prof. Seth Teller
Configuration Space for Motion Planning RSS Lecture 10 Monday, 8 March 2010 Prof. Seth Teller Siegwart & Nourbahksh S 6.2 (Thanks to Nancy Amato, Rod Brooks, Vijay Kumar, and Daniela Rus for some of the
More information15-494/694: Cognitive Robotics
15-494/694: Cognitive Robotics Dave Touretzky Lecture 9: Path Planning with Rapidly-exploring Random Trees Navigating with the Pilot Image from http://www.futuristgerd.com/2015/09/10 Outline How is path
More informationProbabilistic roadmaps for efficient path planning
Probabilistic roadmaps for efficient path planning Dan A. Alcantara March 25, 2007 1 Introduction The problem of finding a collision-free path between points in space has applications across many different
More informationLearning to Guide Random Tree Planners in High Dimensional Spaces
Learning to Guide Random Tree Planners in High Dimensional Spaces Jörg Röwekämper Gian Diego Tipaldi Wolfram Burgard Fig. 1. Example paths for a mobile manipulation platform computed with RRT-Connect [13]
More informationJane Li. Assistant Professor Mechanical Engineering Department, Robotic Engineering Program Worcester Polytechnic Institute
Jane Li Assistant Professor Mechanical Engineering Department, Robotic Engineering Program Worcester Polytechnic Institute (3 pts) How to generate Delaunay Triangulation? (3 pts) Explain the difference
More informationWorkspace-Guided Rapidly-Exploring Random Tree Method for a Robot Arm
WorkspaceGuided RapidlyExploring Random Tree Method for a Robot Arm Jaesik Choi choi31@cs.uiuc.edu August 12, 2007 Abstract Motion planning for robotic arms is important for real, physical world applications.
More informationApprenticeship Learning for Reinforcement Learning. with application to RC helicopter flight Ritwik Anand, Nick Haliday, Audrey Huang
Apprenticeship Learning for Reinforcement Learning with application to RC helicopter flight Ritwik Anand, Nick Haliday, Audrey Huang Table of Contents Introduction Theory Autonomous helicopter control
More informationCHAPTER SIX. the RRM creates small covering roadmaps for all tested environments.
CHAPTER SIX CREATING SMALL ROADMAPS Many algorithms have been proposed that create a roadmap from which a path for a moving object can be extracted. These algorithms generally do not give guarantees on
More informationCan work in a group of at most 3 students.! Can work individually! If you work in a group of 2 or 3 students,!
Assignment 1 is out! Due: 26 Aug 23:59! Submit in turnitin! Code + report! Can work in a group of at most 3 students.! Can work individually! If you work in a group of 2 or 3 students,! Each member must
More informationIntroduction to Robotics
Jianwei Zhang zhang@informatik.uni-hamburg.de Universität Hamburg Fakultät für Mathematik, Informatik und Naturwissenschaften Technische Aspekte Multimodaler Systeme 05. July 2013 J. Zhang 1 Task-level
More informationMotion Planning with Dynamics, Physics based Simulations, and Linear Temporal Objectives. Erion Plaku
Motion Planning with Dynamics, Physics based Simulations, and Linear Temporal Objectives Erion Plaku Laboratory for Computational Sensing and Robotics Johns Hopkins University Frontiers of Planning The
More informationInverse Kinematics (part 1) CSE169: Computer Animation Instructor: Steve Rotenberg UCSD, Winter 2018
Inverse Kinematics (part 1) CSE169: Computer Animation Instructor: Steve Rotenberg UCSD, Winter 2018 Welman, 1993 Inverse Kinematics and Geometric Constraints for Articulated Figure Manipulation, Chris
More informationarxiv: v2 [cs.ro] 29 Jul 2016
Scaling Sampling based Motion Planning to Humanoid Robots Yiming Yang, Vladimir Ivan, Wolfgang Merkt, Sethu Vijayakumar arxiv:1607.07470v2 [cs.ro] 29 Jul 2016 Abstract Planning balanced and collision free
More informationVisibility Graph. How does a Mobile Robot get from A to B?
Robot Path Planning Things to Consider: Spatial reasoning/understanding: robots can have many dimensions in space, obstacles can be complicated Global Planning: Do we know the environment apriori? Online
More informationEG-RRT: Environment-Guided Random Trees for Kinodynamic Motion Planning with Uncertainty and Obstacles
EG-RRT: Environment-Guided Random Trees for Kinodynamic Motion Planning with Uncertainty and Obstacles Léonard Jaillet, Judy Hoffman, Jur van den Berg, Pieter Abbeel, Josep M. Porta, Ken Goldberg Abstract
More informationUniform and Efficient Exploration of State Space using Kinodynamic Sampling-based Planners
Uniform and Efficient Exploration of State Space using Kinodynamic Sampling-based Planners Rakhi Motwani, Mukesh Motwani, and Frederick C. Harris Jr. Abstract Sampling based algorithms such as RRTs have
More informationEfficient and Smooth RRT Motion Planning Using a Novel Extend Function for Wheeled Mobile Robots
Efficient and Smooth RRT Motion Planning Using a Novel Extend Function for Wheeled Mobile Robots Luigi Palmieri and Kai O. Arras Social Robotics Laboratory Dept. of Computer Science University of Freiburg
More informationFACOLTÀ DI INGEGNERIA DELL INFORMAZIONE ELECTIVE IN ROBOTICS. Quadrotor. Motion Planning Algorithms. Academic Year
FACOLTÀ DI INGEGNERIA DELL INFORMAZIONE ELECTIVE IN ROBOTICS Quadrotor Motion Planning Algorithms Prof. Marilena Vendittelli Prof. Jean-Paul Laumond Jacopo Capolicchio Riccardo Spica Academic Year 2010-2011
More informationFeedback Motion Planning via Non-holonomic RRT for Mobile Robots
Feedback Motion Planning via Non-holonomic RRT for Mobile Robots Jong Jin Park 1 and Benjamin Kuipers 2 Abstract Here we present a non-holonomic distance function for unicycle-type vehicles, and use this
More informationvizmo++: a Visualization, Authoring, and Educational Tool for Motion Planning
vizmo++: a Visualization, Authoring, and Educational Tool for Motion Planning Aimée Vargas E. Jyh-Ming Lien Nancy M. Amato. aimee@cs.tamu.edu neilien@cs.tamu.edu amato@cs.tamu.edu Technical Report TR05-011
More informationUsing Classical Planners for Tasks with Con5nuous Ac5ons in Robo5cs
Using Classical Planners for Tasks with Con5nuous Ac5ons in Robo5cs Stuart Russell Joint work with Siddharth Srivastava, Lorenzo Riano, Pieter Abbeel Using Classical Planners for Tasks with Con5nuous Ac5ons
More informationCognitive Robotics Robot Motion Planning Matteo Matteucci
Cognitive Robotics Robot Motion Planning Robot Motion Planning eminently necessary since, by definition, a robot accomplishes tasks by moving in the real world. J.-C. Latombe (1991) Robot Motion Planning
More informationVehicle Motion Planning with Time-Varying Constraints
Vehicle Motion Planning with Time-Varying Constraints W. Todd Cerven 1, Francesco Bullo 2, and Victoria L. Coverstone 3 University of Illinois at Urbana-Champaign Introduction With the growing emphasis
More informationSub-optimal Heuristic Search and its Application to Planning for Manipulation
Sub-optimal Heuristic Search and its Application to Planning for Manipulation Mike Phillips Slides adapted from Planning for Mobile Manipulation What planning tasks are there? robotic bartender demo at
More informationIntroduction to Intelligent System ( , Fall 2017) Instruction for Assignment 2 for Term Project. Rapidly-exploring Random Tree and Path Planning
Instruction for Assignment 2 for Term Project Rapidly-exploring Random Tree and Path Planning Introduction The objective of this semester s term project is to implement a path planning algorithm for a
More informationHuman-Oriented Robotics. Robot Motion Planning. Kai Arras Social Robotics Lab, University of Freiburg
Robot Motion Planning Kai Arras, University of Freiburg 1 Contents Introduction Configuration space Combinatorial planning Sampling-based planning Potential fields methods A, Any-Angle A, D/D Lite Dynamic
More informationRobotics. Chapter 25. Chapter 25 1
Robotics Chapter 25 Chapter 25 1 Outline Robots, Effectors, and Sensors Localization and Mapping Motion Planning Chapter 25 2 Mobile Robots Chapter 25 3 Manipulators P R R R R R Configuration of robot
More informationPath Planning among Movable Obstacles: a Probabilistically Complete Approach
Path Planning among Movable Obstacles: a Probabilistically Complete Approach Jur van den Berg 1, Mike Stilman 2, James Kuffner 3, Ming Lin 1, and Dinesh Manocha 1 1 Department of Computer Science, University
More informationSuper Assembling Arms
Super Assembling Arms Yun Jiang, Nan Xiao, and Hanpin Yan {yj229, nx27, hy95}@cornell.edu Abstract Although there are more and more things personal robots can do for us at home, they are unable to accomplish
More informationDiscrete search algorithms
Robot Autonomy (16-662, S13) Lecture#08 (Monday February 11) Discrete search algorithms Lecturer: Siddhartha Srinivasa Scribes: Kavya Suresh & David Matten I. INTRODUCTION These notes contain a detailed
More informationvideo 1 video 2 Motion Planning (It s all in the discretization) Digital Actors Basic problem Basic problem Two Possible Discretizations
Motion Planning (It s all in the discretization) Motion planning is the ability for an agent to compute its own motions in order to achieve certain goals. ll autonomous robots and digital actors should
More informationApproaches for Heuristically Biasing RRT Growth
Approaches for Heuristically Biasing RRT Growth Chris Urmson & Reid Simmons The Robotics Institute, Carnegie Mellon University, Pittsburgh, USA {curmson, reids}@ri.cmu.edu Abstract This paper presents
More informationPath Planning in Repetitive Environments
MMAR 2006 12th IEEE International Conference on Methods and Models in Automation and Robotics 28-31 August 2006 Międzyzdroje, Poland Path Planning in Repetitive Environments Jur van den Berg Mark Overmars
More informationClustering Color/Intensity. Group together pixels of similar color/intensity.
Clustering Color/Intensity Group together pixels of similar color/intensity. Agglomerative Clustering Cluster = connected pixels with similar color. Optimal decomposition may be hard. For example, find
More informationFinal project: 45% of the grade, 10% presentation, 35% write-up. Presentations: in lecture Dec 1 and schedule:
Announcements PS2: due Friday 23:59pm. Final project: 45% of the grade, 10% presentation, 35% write-up Presentations: in lecture Dec 1 and 3 --- schedule: CS 287: Advanced Robotics Fall 2009 Lecture 24:
More informationIntroduction to Mobile Robotics Path and Motion Planning. Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello
Introduction to Mobile Robotics Path and Motion Planning Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Diego Tipaldi, Luciano Spinello 1 Motion Planning Latombe (1991): eminently necessary since,
More informationSPATIAL GUIDANCE TO RRT PLANNER USING CELL-DECOMPOSITION ALGORITHM
SPATIAL GUIDANCE TO RRT PLANNER USING CELL-DECOMPOSITION ALGORITHM Ahmad Abbadi, Radomil Matousek, Pavel Osmera, Lukas Knispel Brno University of Technology Institute of Automation and Computer Science
More informationPlanning in Mobile Robotics
Planning in Mobile Robotics Part I. Miroslav Kulich Intelligent and Mobile Robotics Group Gerstner Laboratory for Intelligent Decision Making and Control Czech Technical University in Prague Tuesday 26/07/2011
More informationAnnouncements. Recap Landmark based SLAM. Types of SLAM-Problems. Occupancy Grid Maps. Grid-based SLAM. Page 1. CS 287: Advanced Robotics Fall 2009
Announcements PS2: due Friday 23:59pm. Final project: 45% of the grade, 10% presentation, 35% write-up Presentations: in lecture Dec 1 and 3 --- schedule: CS 287: Advanced Robotics Fall 2009 Lecture 24:
More informationStable Trajectory Design for Highly Constrained Environments using Receding Horizon Control
Stable Trajectory Design for Highly Constrained Environments using Receding Horizon Control Yoshiaki Kuwata and Jonathan P. How Space Systems Laboratory Massachusetts Institute of Technology {kuwata,jhow}@mit.edu
More information15-780: MarkovDecisionProcesses
15-780: MarkovDecisionProcesses J. Zico Kolter Feburary 29, 2016 1 Outline Introduction Formal definition Value iteration Policy iteration Linear programming for MDPs 2 1988 Judea Pearl publishes Probabilistic
More informationCollided Path Replanning in Dynamic Environments Using RRT and Cell Decomposition Algorithms
Collided Path Replanning in Dynamic Environments Using RRT and Cell Decomposition Algorithms Ahmad Abbadi ( ) and Vaclav Prenosil Department of Information Technologies, Faculty of Informatics, Masaryk
More informationNavigation and Metric Path Planning
Navigation and Metric Path Planning October 4, 2011 Minerva tour guide robot (CMU): Gave tours in Smithsonian s National Museum of History Example of Minerva s occupancy map used for navigation Objectives
More informationOptimal Kinodynamic Motion Planning using Incremental Sampling-based Methods
Optimal Kinodynamic Motion Planning using Incremental Sampling-based Methods The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Citation
More informationCan we quantify the hardness of learning manipulation? Kris Hauser Department of Electrical and Computer Engineering Duke University
Can we quantify the hardness of learning manipulation? Kris Hauser Department of Electrical and Computer Engineering Duke University Robot Learning! Robot Learning! Google used 14 identical robots 800,000
More informationExperience Guided Mobile Manipulation Planning
Experience Guided Mobile Manipulation Planning Tekin Meriçli 1 and Manuela Veloso 2 and H. Levent Akın 1 {tekin.mericli,akin}@boun.edu.tr,veloso@cmu.edu 1 Department of Computer Engineering, Boğaziçi University,
More informationCase-Based Reasoning. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. Parametric / Non-parametric.
CS 188: Artificial Intelligence Fall 2008 Lecture 25: Kernels and Clustering 12/2/2008 Dan Klein UC Berkeley Case-Based Reasoning Similarity for classification Case-based reasoning Predict an instance
More information