Robotics 14 AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 1 14 - - PowerPoint PPT Presentation

Robotics

14

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 1

14 Robotics∗ 14.1 Robots 14.2 Hardware 14.3 Perception 14.4 Motion planning 14.5 Controllor 14.6 Software

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 2

Robots

Robots are physical agents that perform tasks by manipulating the physical world Wide application: Industry, Agriculture, Transportation, Health, En- vironments, Exploration, Personal Services, Entertainment, Human augmentation and so on ⇐ Robotic age ⇒ Intelligent Robots

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 3

Types of robots

• Manipulators: physically anchored to their workplace

e.g., factory assembly line, the International Space Station

• Mobile robots: move about their environment

– Unmanned ground vehicles (UGVs), e.g., The planetary Rover (in Mars), intelligent vehicles – Unmanned air vehicles (UAVs), i.e., drone – Autonomous underwater vehicles (AUVs) – Autonomous fight unit

• Mobile manipulator: combined mobility with manipulation

– Humanoid robots: mimic the human torso Other: prosthetic devices (e.g., artificial limbs), intelligent environ- ments (e.g., house equipped with sensors and effectors), multibody systems (swarms of small cooperating robots)

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 4

Hardware

A diverse set of robot hardware comes from interdisciplinary tech- nologies – Processors (controllors) – Sensors – Effectors – – Manipulators

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 5

Sensors

Passive sensors or active sensors – Range finders: sonar (land, underwater), laser range finder, radar (aircraft), tactile sensors, GPS – Imaging sensors: cameras (visual, infrared) – Proprioceptive sensors: shaft decoders (joints, wheels), inertial sen- sors, force sensors, torque sensors

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 6

Manipulators

R R R P R R

Configuration of robot specified by 6 numbers ⇒ 6 degrees of freedom (DOF) 6 is the minimum number required to position end-effector arbitrarily. For dynamical systems, add velocity for each DOF.

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 7

Non-holonomic robots

θ

(x, y)

A car has more DOF (3) than controls (2), so is non-holonomic; cannot generally transition between two infinitesimally close configu- rations

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 8

Perception

Perception: the process mapping sensor measurements into internal representations of the environment – sensors: noisy – environment: partially observable, unpredictable, dynamic HMMs or DBNs can represent the transition and sensor models of a partially observable environment DNNs can recognize vision and various objects – the best internal representation is not known – unsupervised learning to learn sensor and motion models from data

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 9

Perception generally

Stimulus (percept) S, World W S = g(W) E.g., g = “graphics”. Can we do vision as inverse graphics? W = g−1(S)

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 10

Perception generally

Stimulus (percept) S, World W S = g(W) E.g., g = “graphics”. Can we do vision as inverse graphics? W = g−1(S) Problem: massive ambiguity!

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 11

Perception generally

Stimulus (percept) S, World W S = g(W) E.g., g = “graphics.” Can we do vision as inverse graphics? W = g−1(S) Problem: massive ambiguity!

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 12

Perception generally

Stimulus (percept) S, World W S = g(W) E.g., g = “graphics.” Can we do vision as inverse graphics? W = g−1(S) Problem: massive ambiguity!

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 13

Localization

Compute current location and orientation (pose) given observations (DBN)

Xt+1 Xt At−2 At−1 At Zt−1 Xt−1 Zt Zt+1

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 14

Localization

xi, yi vt Δt xt+1 h(xt) xt θt

t+1

θ

t Δt

ω

Z1 Z2 Z3 Z4

Assume Gaussian noise in motion prediction, sensor range measure- ments

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 15

Localization

Can use particle filtering to produce approximate position estimate

Robot position Robot position (b) Robot position (c)

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 16

Localization

Can also use extended Kalman filter for simple cases:

robot landmark

Assumes that landmarks are identifiable — otherwise, posterior is multimodal

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 17

Mapping

Localization: given map and observed landmarks, update pose distri- bution Mapping: given pose and observed landmarks, update map distribu- tion SLAM: given observed landmarks, update pose and map distribution Probabilistic formulation of SLAM (simultaneous localization and map- ping): add landmark locations L1, . . . , Lk to the state vector, proceed as for localization

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 18

Motion Planning

Path planning: find a path from one configuration to another – various path planning algorithms in discrete spaces – path plan vs. task plan Continuous spaces: plan in configuration space defined by the robot’s DOFs

conf-3 conf-1 conf-2 conf-3 conf-2 conf-1 e s s e

Solution is a point trajectory in free C-space

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 19

Configuration space planning

Basic problem: ∞d states! Convert to finite state space Cell decomposition: divide up space into simple cells each of which can be traversed “easily” (e.g., convex) become discrete graph search problem Skeletonization: reduce the free space to a one-dimensional representation identify finite number of easily connected points/lines that form a graph s.t. any two points are connected by a path on the graph

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 20

Cell decomposition example

2DOFs robot arm workspace coordinates configuration space

start goal

start goal

Problem: may be no path in pure freespace (white area) cells Solution: recursive decomposition of mixed (free+obstacle) cells

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 21

Skeletonization: Voronoi diagram

Voronoi diagram: locus of points equidistant from obstacles Problem: doesn’t scale well to higher dimensions

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 22

Skeletonization: probabilistic roadmap

A probabilistic roadmap is generated by random points in C-space and keeping those in freespace; create graph by joining pairs by straight lines Problem: need to generate enough points to ensure that every start/goal pair is connected through the graph

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 23

Controllor

Can view the motor control problem as a search problem in the dynamic rather than kinematic state space: – state space defined by x1, x2, . . . , ˙ x1, ˙ x2, . . . – continuous, high-dimensional Deterministic control: many problems are exactly solvable

• esp. if linear, low-dimensional, exactly known, observable

Simple regulatory control laws are effective for specified motions Stochastic optimal control: very few problems exactly solvable ⇒ approximate/adaptive methods

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 24

Biological motor control

Motor control systems are characterized by massive redundancy Infinitely many trajectories achieve any given task E.g., 3-link arm moving in plane throwing at a target simple 12-parameter controller, one degree of freedom at target 11-dimensional continuous space of optimal controllers Idea: if the arm is noisy, only “one” optimal policy minimizes error at target I.e., noise-tolerance might explain actual motor behaviour

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 25

Software

Software architecture (of a robot car)

Touareg interface Laser mapper Wireless E-Stop Top level control Laser 2 interface Laser 3 interface Laser 4 interface Laser 1 interface Laser 5 interface Camera interface Radar interface Radar mapper Vision mapper UKF Pose estimation Wheel velocity GPS position GPS compass IMU interface Surface assessment Health monitor Road finder Touch screen UI Throttle/brake control Steering control Path planner

laser map vehicle state (pose, velocity) velocity limit map vision map vehicle state

• bstacle list

trajectory road center

RDDF database

driving mode pause/disable command

Power server interface

clocks emergency stop power on/off Linux processes start/stop heart beats corridor

SENSOR INTERFACE PERCEPTION PLANNING&CONTROL USER INTERFACE VEHICLE INTERFACE

RDDF corridor (smoothed and original)

Process controller

GLOBAL SERVICES

health status data

Data logger File system

Communication requests vehicle state (pose, velocity)

Brake/steering

Communication channels

Inter-process communication (IPC) server Time server

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 26

Pipeline architecture

Execute multiple processes in parallel – sensor interface layer – perception layer – planning and control layer – vehicle interface layer

AI Slides (5e) c Lin Zuoquan@PKU 2003-2019 14 27