CS 326 A: Motion Planning

1
CS 326 A Motion Planning

• URL http//robotics.stanford.edu/latombe/cs326/2
  000
• Instructor Jean-Claude Latombe
• Teaching Assistant Carlos Guestrin
• Computer Science Department
• Stanford University

2
Goal of Motion Planning

• Compute motion strategies, e.g.
• geometric paths
• time-parameterized trajectories
• sequence of sensor-based motion commands
• To achieve high-level goals, e.g.
• go to A without colliding with obstacles
• assemble product P
• build map of environment E
• find object O

3
Is It Easy?
4
Basic Problem

• Statement Compute a collision-free path for a
  rigid or articulated object (the robot) among
  static obstacles
• Inputs
• Geometry of robot and obstacles
• Kinematics of robot (degrees of freedom)
• Initial and goal robot configurations
  (placements)
• Outputs
• Continuous sequence of collision-free robot
  configurations connecting the initial and goal
  configurations

5
Example with Rigid Object
6
Example with Rigid Object
7
Example with Articulated Object
8
Example with Articulated Object
9
Some Extensions to the Basic Problem

• Moving obstacles
• Multiple robots
• Movable objects
• Assembly planning
• Goal is to acquire information by sensing
• Model building
• Object finding/tracking
• Nonholonomic constraints

• Dynamic constraints
• Optimal planning
• Uncertainty in control and sensing
• Exploiting task mechanics (sensorless motions)
• Physical models and deformable objects
• Integration of planning and control

10
Moving Obstacles and Dynamic Constraints
11
Planning in Dynamic Unpredictable Environment
12
Some Extensions to the Basic Problem

• Moving obstacles
• Multiple robots
• Movable objects
• Assembly planning
• Goal is to acquire information by sensing
• Model building
• Object finding/tracking
• Nonholonomic constraints

• Dynamic constraints
• Optimal planning
• Uncertainty in control and sensing
• Exploiting task mechanics (sensorless motions)
• Physical models and deformable objects
• Integration of planning and control

13
Assembly Planning
14
Some Extensions to the Basic Problem

• Moving obstacles
• Multiple robots
• Movable objects
• Assembly planning
• Goal is to acquire information by sensing
• Model building
• Object finding/tracking
• Nonholonomic constraints

• Dynamic constraints
• Optimal planning
• Uncertainty in control and sensing
• Exploiting task mechanics (sensorless motions)
• Physical models and deformable objects
• Integration of planning and control

15
Map Building
Where to move next?
16
Planning Target-Finding Strategies
17
Planning Target-Tracking Strategies
18
Some Extensions to the Basic Problem

• Moving obstacles
• Multiple robots
• Movable objects
• Assembly planning
• Goal is to acquire information by sensing
• Model building
• Object finding/tracking
• Nonholonomic constraints

• Dynamic constraints
• Optimal planning
• Uncertainty in control and sensing
• Exploiting task mechanics (sensorless motions)
• Physical models and deformable objects
• Integration of planning and control

19
Planning for Nonholonomic Robots
20
Some Extensions to the Basic Problem

• Moving obstacles
• Multiple robots
• Movable objects
• Assembly planning
• Goal is to acquire information by sensing
• Model building
• Object finding/tracking
• Nonholonomic constraints

• Dynamic constraints
• Optimal planning
• Uncertainty in control and sensing
• Exploiting task mechanics (sensorless motions)
• Physical models and deformable objects
• Integration of planning and control

21
Planning with Uncertainty in Sensing and Control
W2
I
G
W1
22
Some Extensions to the Basic Problem

• Moving obstacles
• Multiple robots
• Movable objects
• Assembly planning
• Goal is to acquire information by sensing
• Model building
• Object finding/tracking
• Nonholonomic constraints

• Dynamic constraints
• Optimal planning
• Uncertainty in control and sensing
• Exploiting task mechanics (sensorless motions)
• Physical models and deformable objects
• Integration of planning and control

23
Motion Planning for Deformable Objects
24
Examples of Applications

• Manufacturing
• Robot programming
• Robot placement
• Design of part feeders
• Design for manufacturing and servicing
• Design of pipe layouts and cable harnesses
• Autonomous mobile robots planetary exploration,
  surveillance, military scouting

• Graphic animation of digital actors for video
  games, movies, and webpages
• Medical surgery planning
• Generation of plausible molecule motions, e.g.,
  docking and folding motions
• Building code verification

25
Robot Programming and Robot Placement
26
Examples of Applications

• Manufacturing
• Robot programming
• Robot placement
• Design of part feeders
• Design for manufacturing and servicing
• Design of pipe layouts and cable harnesses
• Autonomous mobile robots planetary exploration,
  surveillance, military scouting

• Graphic animation of digital actors for video
  games, movies, and webpages
• Medical surgery planning
• Generation of plausible molecule motions, e.g.,
  docking and folding motions
• Building code verification

27
Design for Manufacturing
Automobile compartment, General Motors
28
Design for Maintainability
Aircraft engine, General Electric
29
Examples of Applications

• Manufacturing
• Robot programming
• Robot placement
• Design of part feeders
• Design for manufacturing and servicing
• Design of pipe layouts and cable harnesses
• Autonomous mobile robots planetary exploration,
  surveillance, military scouting

• Graphic animation of digital actors for video
  games, movies, and webpages
• Medical surgery planning
• Generation of plausible molecule motions, e.g.,
  docking and folding motions
• Building code verification

30
Military Scouting in Outdoor Environment
31
Examples of Applications

• Manufacturing
• Robot programming
• Robot placement
• Design of part feeders
• Design for manufacturing and servicing
• Design of pipe layouts and cable harnesses
• Autonomous mobile robots planetary exploration,
  surveillance, military scouting

• Graphic animation of digital actors for video
  games, movies, and webpages
• Medical surgery planning
• Generation of plausible molecule motions, e.g.,
  docking and folding motions
• Building code verification

32
Digital Actors
A Bugs Life (Pixar/Disney)
Toy Story (Pixar/Disney)
Antz (Dreamworks)
Tomb Raider 3 (Eidos Interactive)
Final Fantasy VIII (SquareOne)
The Legend of Zelda (Nintendo)
33
Motion Planning for Digital Actors
Manipulation
Sensory-based locomotion
34
Examples of Applications

• Manufacturing
• Robot programming
• Robot placement
• Design of part feeders
• Design for manufacturing and servicing
• Design of pipe layouts and cable harnesses
• Autonomous mobile robots planetary exploration,
  surveillance, military scouting

• Graphic animation of digital actors for video
  games, movies, and webpages
• Medical surgery planning
• Generation of plausible molecule motions, e.g.,
  docking and folding motions
• Building code verification

35
Radiosurgical Planning
Cross-firing at a tumor while sparing healthy
critical tissue
36
Examples of Applications

• Manufacturing
• Robot programming
• Robot placement
• Design of part feeders
• Design for manufacturing and servicing
• Design of pipe layouts and cable harnesses
• Autonomous mobile robots planetary exploration,
  surveillance, military scouting

• Graphic animation of digital actors for video
  games, movies, and webpages
• Medical surgery planning
• Generation of plausible molecule motions, e.g.,
  docking and folding motions
• Building code verification

37
Generation of Plausible Docking Motions
Ligand-receptor docking
38
Examples of Applications

• Manufacturing
• Robot programming
• Robot placement
• Design of part feeders
• Design for manufacturing and servicing
• Design of pipe layouts and cable harnesses
• Autonomous mobile robots planetary exploration,
  surveillance, military scouting

• Graphic animation of digital actors for video
  games, movies, and webpages
• Medical surgery planning
• Generation of plausible molecule motions, e.g.,
  docking and folding motions
• Building code verification

39
Building Code Verification
40
Goals of CS326A

• Present a coherent framework for formulating and
  solving motion planning problems
• configuration space and related spaces
• random sampling and cell decomposition algorithms
• Illustration by examples drawn from mechanical
  design, manufacturing, graphic animation, medical
  surgery, and computational biology
• Emphasis of practical algorithms with
  guarantees of performance over theoretical or
  purely heuristic algorithms

41
Practical Algorithms

• A complete motion planner always returns a valid
  plan when one exists and indicates that no such
  plan exists otherwise
• Most motion problems are hard complete planners
  take exponential time in of degrees of freedom,
  objects, etc
• Theoretical algorithms strive for completeness
  and minimal worst-case complexity. Difficult to
  implement and not robust
• Heuristic algorithms strive for efficiency in
  commonly encountered situations. Usually no
  performance guarantee
• Weaker completeness
  Simplifying assumptions Exponential
  algorithms that work in practice

42
Prerequisites

• Ability and willingness to complete a significant
  programming project with simple graphic interface
• Basic knowledge and taste for geometry and
  algorithms
• Willingness to devote some time each week to read
  at least two papers

43
Requirements

• Attend every class
• Prepare/give two inclass presentations (20 min
  each)
• Read at least one of the two papers listed as
  required reading prior to each class
• Complete the programming project

44
Schedule (1/2)
45
Schedule (2/2)
46
Programming Project (1/2)

• Proposed projectImplement a Probabilistic
  Roadmap planner
• Possible specific example
• Robot and obstacles are discs/spheres
• Some obstacles are static others move at
  constant velocities
• Robots velocity is bounded
• Variations
• There are several robots to coordinate
• Each robots acceleration is bounded
• Robot is articulated linkage

47
Programming project (2/2)

• Study various sampling strategies, impact of
  collision checking technique, convergence of
  planner, etc.
• Possibility of customized projects

48
Final Presentation of Programming Project

• Write short report (2-5 pages) describing
  software what it does, what techniques have been
  used, what experiments have been done, what
  results have been obtained
• Give live presentation of software and answer
  questions.
• Make report available on the web, plus (optional)
  a java applet.