+ All Categories
Home > Documents > Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive...

Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive...

Date post: 22-May-2020
Category:
Upload: others
View: 5 times
Download: 0 times
Share this document with a friend
44
Autonomous Mobile Robots and Intelligent Control Issues Sven Seeland
Transcript
Page 1: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

Autonomous Mobile Robots and Intelligent Control Issues

Sven Seeland

Page 2: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

2

Overview

● Introduction

● Motivation● History of Autonomous Cars

● DARPA Grand Challenge

● History and Rules● Controlling Autonomous Cars

● MIT Talos Overview● Intelligent Control Systems● Controlling Talos

Page 3: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

3

Mobile Robots – Motivations

● Can work under hostile environmental conditions

● Can move in confined spaces

● Expendable in dangerous situations

Page 4: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

4

Autonomy – Definition 1

“Autonomy refers to systems capable of operating in the real-world environment without any form of

external control for extended periods of time.”George A. Bekey, Autonomous Robots: from biological inspiration to implementation and control

Page 5: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

5

Autonomy – Definition 2

A fully autonomous robot has the ability to

● Gain information about the environment.● Work for an extended period without human intervention.● Move either all or part of itself throughout its operating

environment without human assistance.● Avoid situations that are harmful to people, property, or itself

unless those are part of its design specifications.

- Wikipedia, “Autonomous robot”

Page 6: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

6

Autonomy – Motivations

● Remote control might be infeasible

● Area too large or cluttered for wired control● Poor wireless reception

● No operator required

● Cheap operation of many units● No set working hours● No fatigue

Page 7: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

7

Autonomous Mobile Robots – Applications

● Clearing an area of landmines, bombs and other explosives

● Rescue robots

● Service Robots

● Maintenance Robots

● Exploration

● Toys

● Automated Driving

● ...

Page 8: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

8

Autonomous Cars – Motivation

● Public Transport

● Safer Driving

● More comfortable traveling

● Delivery Tasks

● ...

Page 9: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

9

Overview

● Introduction

● Motivation● History of Autonomous Cars

● DARPA Grand Challenge

● History and Rules● Controlling Autonomous Cars

● MIT Talos Overview● Intelligent Control Systems● Controlling Talos

Page 10: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

10

Autonomous Cars – History

● PROMETHEUS Project (1989-1995)

● Initiated by the European Commission● PROgraMme for a European Traffic of Highest

Efficiency and Unprecedented Safety● $1 billion funding● Most prominent results where VaMP and ARGO

Page 11: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

11

Autonomous Cars – History

● VaMP (1995)

● Versuchsfahrzeug für autonome Mobilität PKW● >2000 km from Munich to Kopenhagen and back in

normal traffic● Up to 180 km/h● Up to 158 km without human intervention● Mean distance between human interventions: 9 km● Lane changes● Vehicle passing● Active computer vision● Radar

Page 12: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

12

Autonomous Cars – History

● ARGO Project (1998)

● 2000 km Tour through Italy● Above 90% of the time in automatic mode● Longest distance without intervention: 54.3 km● Two cameras● 200 MHz Pentium MMX

Page 13: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

13

Overview

● Introduction

● Motivation● History of Autonomous Cars

● DARPA Grand Challenge

● History and Rules● Controlling Autonomous Cars

● MIT Talos Overview● Intelligent Control Systems● Controlling Talos

Page 14: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

14

DARPA Grand Challenge - History

● Motivation: Make one-third of ground military forces autonomous by 2015

● Off-road tracks

● 2004:

● 241 km

● $1 Million prize money

● no winner

● Best vehicle travelled 11,78 km

● 2005:

● 213 km

● $2 Million prize money

● 5 vehicles succeed

● All but one got past the maximum distance of 2004

Page 15: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

15

DARPA Urban Challenge 2007 – Rules 1

● $2 Million, $1 Million and $500.000 prizes

● Complete 60 miles in 6 hours to finish the race

● Urban environment

● Decommissioned Air Force Base● Street network in residential area● Several dirt roads

● Obey traffic laws

● All cars on the course at the same time

● 3 individual missions per car

● No pedestrians or other moving objects

● Time penalties for dangerous or erroneous behavior

Page 16: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

16

DARPA Urban Challenge 2007 – Rules 2

● One Route Network Definition File (RNDF)

● Handed out 24 hours before the race● Similar to maps used in GPS navigation systems● Contains road positions, number of lanes, intersections,

parking space locations in GPS coordinates● One Mission Description File per Team and Mission (MDF)

● Handed out on the day of the event● Contains a list of checkpoints from the RNDF that the

vehicle needs to cross

Page 17: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

17

Overview

● Introduction

● Motivation● History of Autonomous Cars

● DARPA Grand Challenge

● History● Rules

● Controlling Autonomous Cars

● MIT Talos Overview● Intelligent Control Systems● Controlling Talos

Page 18: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

18

MIT Talos

Page 19: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

19

MIT Talos – Design Considerations

● Many low-cost sensors

● Increases perception robustness● More complete coverage● Higher efficiency in a multi-processor environment

● Minimal reliance on GPS data

● Highly distributed computer

● Better reaction times● Downside: higher power consumption

● Simple low level controls

● Improve robustness● Minimal sensor fusion / asynchronous sensor update

Page 20: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

20

MIT Talos – Specifications

● Land Rover LR3

● Human drivable

● EMC AEVIT drive-by-wire system

● 6000 Watts power generator

● 2 ruggedized UPS

● Blade Cluster (10 x 4 64-bit CPUs, 2.3 GHz each)

● Velodyne HDL-64 LIDAR (3D)

● 12 SICK LIDARs (2D)

● 5 cameras (752x480, 22.8 images per second)

● 15 millimeter wave radars

● Applanix navigation solution (GPS, inertial measurement unit and wheel encoder)

Page 21: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

21

Overview

● Introduction

● Motivation● History of Autonomous Cars

● DARPA Grand Challenge

● History● Rules

● Controlling Autonomous Cars

● MIT Talos Overview● Intelligent Control Systems● Controlling Talos

Page 22: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

22

Intelligent Control Systems – Tasks

● Actuation● Collision avoidance● Path-finding / Trajectory planning● Mission planning● Localization

Page 23: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

23

Intelligent Control Systems – Challenges

● Uncertainty

● Dynamic environment● Perception● Actuation

● Efficiency

● Short reaction times in a dynamic environment● Limited processing power due to limited space on the

moving platform● Scalability

● Potentially huge environment● Potentially long operating times

Page 24: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

24

Intelligent Control Systems – Requirements

● Robustness

● Input is likely to be inaccurate, incomplete or wrong● Unforeseen conditions are likely to occur

● Speed

● Quickly react to situations● Initial assumptions may be invalid by the time the

deliberation process is finished● Versatility

● Multitude of tasks need to be executed simultaneously● Highly diverse nature of tasks

Page 25: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

25

Intelligent Control Systems – Basics

● Control Systems consist of:

● Input● Controller● Output

Input OutputController

Page 26: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

26

Intelligent Control Systems – Reactive Systems

● Purely reactive systems:

● No planning or learning

● No internal state

● Complexity of tasks is limited

● Highly robust

● Very quick reaction times

World

Perception Decision Action

Page 27: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

27

Intelligent Control Systems – Deliberative Systems

● Deliberative Systems

● Allows for planning and learning

● Internal world model

● Can perform very complex tasks

● Not very robust

● Slow

Programming

Perception

Knowledge DecisionsReasoning

Actions

World

Model Building Decision Making

Page 28: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

28

Intelligent Control Systems – Hybrid Systems 1

● Hybrid Systems

● Combination of systems

● Reactive systems for short term reactions and low level controls

● Deliberative systems for planning and coordination

Programming

Perception

Knowledge DecisionsReasoning

Actions

World

Model Building Decision Making

Page 29: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

29

Intelligent Control Systems – Hybrid Systems

● Oftentimes organized in three layers

● Planning layer handles long time action plans

● Sequencing divides long term goals into smaller steps

● Controlling translates those steps into actual actuator commands

● Layers operate in parallel and independently

● Low layers can fail and report failure to higher layers

● Higher layers tend to use deliberative approaches

● Lower layers tend to use reactive approaches

Planning

Sequencing

Controlling

Page 30: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

30

Overview

● Introduction

● Motivation● History of Autonomous Cars

● DARPA Grand Challenge

● History● Rules

● Controlling Autonomous Cars

● MIT Talos Overview● Intelligent Control Systems● Controlling Talos

Page 31: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

31

MIT Talos – Control System Architecture

Page 32: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

32

MIT Talos – IPC Infrastructure

● LCM – lightweight communications and marshaling

● Minimalist system for real-time applications

● Developed specifically for Talos

● Based on UDP-Multicast

● Publish/subscribe message-passing model

● Logging made extremely easy

● Freely available

Page 33: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

33

MIT Talos – Control System Architecture

Page 34: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

34

MIT Talos – Navigator 1

● Highest level of abstraction

● General planning component● Route planning

● Intersection handling (precedence, crossing, merging)

● Passing

● Blockage replanning

● Turn signaling

● Failsafe timers

● Inputs: MDF, lane information, vehicle pose

● Outputs: goals for motion planner● Short term goals within 40-50m range

● Goal is moved according to the high level intentions

● Timing of the goal-setting used to control motion

Page 35: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

35

MIT Talos – Navigator 2

● Reevaluates situation at 2 Hz● Dynamic replanning comes “for free”

● Passing● Goal remains unchanged

● Checks if other lane exists and is free

● Allows the motion planner to use the other lane

● Two timers for global problem solving:● Failsafe timer

– Progressively sets and unsets global failsafe states

– Failsafe states progressively relax security constraints● Blockage time

– Determines traffic jams and roadblocks

– Only works in two-lane roads where a u-turn is possible

Page 36: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

36

MIT Talos – Control System Architecture

Page 37: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

37

MIT Talos – Drivability Map 1

● Interface to perceptual data

● Influenced by the failsafe states set by the navigator

● Input: Sensory data

● Output: A map, indicating the feasibility of certain paths for the motion planner

● Contains:● Infeasible regions

● Restricted regions

● High cost regions

Page 38: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

38

MIT Talos – Drivability Map 2

Page 39: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

39

MIT Talos – Control System Architecture

Page 40: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

40

MIT Talos – Motion Planner

● Short term path planning

● Input: RNDF goals and situational data from the Navigator, Drivability Map

● Output: Path and Speed commands for the Controller

● Output is sent at 10 Hz

● Rapidly-exploring Random Tree● Generate semi-random waypoints

● Iterate over those waypoints

● Generate a trajectory using closed-loop dynamics

● Check the trajectory for feasibility

Page 41: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

41

MIT Talos – Control System Architecture

Page 42: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

42

MIT Talos - Controller

● Controls the vehicle

● Generates gas, brake, steering and gearshift commands

● Two Controllers

● Pure-Pursuit controller for steering● Two different controllers for forward and reverse

steering● Proportional-Integral controller for speed● Steering lookahead is based on current commanded

speed● Commanded speed is based on vehicle location

Page 43: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

43

References● Leonard, J., How, J., Teller, S. et al. A perception-driven autonomous urban vehicle. In: Journal

of Field Robotics, 25 (2008) Nr. 10, p. 727-774

● DARPA, DARPA Urban Challenge Website, http://www.darpa.mil/grandchallenge/index.asp (2007)

● Team MIT (2007), Technical Report – DARPA Urban Challenge, http://www.darpa.mil/grandchallenge/TechPapers/MIT.pdf (2007)

● Stenzel, R.: Steuerungsarchitekturen für autonome mobile Roboter, Aachen, RWTH, Dissertation, 2002.

● Wikipedia: DARPA Grand Challenge. (2009, December 30) http://en.wikipedia.org/wiki/DARPA_Grand_Challenge

● Wikipedia: Autonome mobile Roboter. (2009, November 21) http://de.wikipedia.org/wiki/Autonome_mobile_Roboter

● Wikipedia: VaMP. (2009, December 14) http://en.wikipedia.org/wiki/VaMP

● ARGO Project Homepage, http://www.argo.ce.unipr.it/ARGO/english/

● Univ.-Prof. Dr.-Ing. Ernst Dieter Dickmanns, Forschungsbericht 1.10.1998 bis 30.9.2002, http://www.unibw.de/rz/dokumente/public/getFILE?fid=bs_999528 (2002)

Page 44: Autonomous Mobile Robots and Intelligent Control …...Intelligent Control Systems – Reactive Systems Purely reactive systems: No planning or learning No internal state Complexity

43

Thank you for your attention!


Recommended