NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

24
NUS CS5247 Planning Motions Planning Motions with Intention with Intention Presented by: Presented by: Yan Ke Yan Ke

Transcript of NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

Page 1: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Planning Motions Planning Motions with Intentionwith Intention

Presented by: Presented by: Yan KeYan Ke

Page 2: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Problem Specification

Task: Generate motions for human or robot arms to complete manipulation tasks.

Goal: Find a collision-free path in configuration space.

Tool: Inverse kinematics algorithm.

Usage: Computer animation.

Page 3: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Page 4: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Difficulties Motion with Intention: Human and robot arms ar

e moving with the intention of completing some task.

Restriction: Neurophysiology.

Grasping and Regrasping: Posture; multiple arms.

PSPACE-hard

Page 5: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Manipulation Manipulation Planning OverviewPlanning Overview

Section Section 11

Page 6: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Inputs

Geometry of the arms

Movable object

Obstacles together with their locations

Initial and goal configuration

Page 7: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

The Stable Space and Grasp Space

Stable space: The set of all configurations where the movable object M is statically stable.

Grasp Space: Arms grasping M and moving it stably.

Grasp Space Stable Space Free Space of the Configuration Space

Page 8: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Transit Paths and Transfer Paths

Transit Paths: Arms motions that do not move M

Transfer Paths: Arms motions that move M

Page 9: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Planning Result

Page 10: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Generating Generating Transfer and Transfer and Transit PathsTransit Paths

Section 2Section 2

Page 11: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Overview The entire manipulation planning can be

accomplished by following:

① Generate a series of subtasks to achieve the goal configuration.

② Plan a transit or transfer path for each subtasks.

Assumption: Transit tasks can be completed by transit paths; transfer tasks can be completed by transfer paths.

Page 12: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Generating Transfer Tasks Grasp set: All various possible grasps for a certa

in M.

Grasp assignment: A pair associates with an element in grasp set and an identity of the grasping arm(s).

We first generate the path for M moving alone.

Secondly, we attach each configuration of M with a list of grasp assignment.

Page 13: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Generating Transfer Tasks The attached list of grasp assignments are obtai

ned by pruning out those no longer possible in the new configuration from the previous configuration.

If somehow we found the list of grasp assignment is empty, then a regrasping is necessary here.

We solve this problem by resetting the list, find all possible of grasp again, and associate them with arm(s).

Page 14: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Assumptions An arm can attain a grasp with a finite set of

different postures.

All arms not involved in the task is placed elsewhere without blocking the motions of working arms.

If M requires two arms to move, any one of them alone, can hold M stably to allow the other one to move in a transit path.

Page 15: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Result A motion planning path for M, each configuration

is attached with a list of grasp assignment.

The path is partitioned into several subpaths by regrasping.

Each subpath is a transfer task.

It does not guarantee to find the best path.

Page 16: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Generating Transit Paths Transit paths are the paths moving the arms.

Connect the initial configuration to the first grasp assignment of the first transfer task.

Connect grasp assignments between different transfer tasks.

Connect the last grasp assignment to the goal configuartion.

Page 17: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Human-Arm Human-Arm KinematicsKinematics

Section 3Section 3

Page 18: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Neurophysiology Goal: Determine the arm posture for a human

arm given the position and orientation of its hand.

Two experimental result:

① Arm and wrist posture are for the most part independent of each other.

② Arm posture for pointing is mainly determined by an ST model.

ST model: Can determine shoulder and elbow joint angles given the position of hand.

Page 19: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Arm Posture

What do we have?

R, ψ, X

What do we want?

θ, β,α,η

Page 20: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Inverse Kinematics Algorithm

Page 21: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Illegal Posture Adjustment

Claim: εis the only one to violate its limits.

Solution: Decrease Φ.

Result: wrist position unchanged when Φ decrease.

Page 22: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Exp

erim

en

tal R

esu

lt

Page 23: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Experimental Result Working environment: C and UNIX.

Time used: three and a half minutes.

Identify the transfer tasks: one and a half minutes.

Different grasp assignments in total: 2600.

Page 24: NUS CS5247 Planning Motions with Intention Presented by: Yan Ke.

NUS CS5247

Conclusion A novel approach to solve the multi-arm

manipulation planning problem.

Computation time is unbounded. If no path exist, the algorithm may run forever.

Aim to create a task-level animation package for human motions.