Research at the Boundary of Robotics and AI: Challenge Problems - - PowerPoint PPT Presentation

▶
research at the boundary of robotics and ai challenge
SMART_READER_LITE
LIVE PREVIEW

Research at the Boundary of Robotics and AI: Challenge Problems - - PowerPoint PPT Presentation

Dec 08, 2023 94 likes •317 views

Research at the Boundary of Robotics and AI: Challenge Problems Prof: Peter Stone Department of Computer Science The University of Texas at Austin Features of Challenges Good performance metrics Peter Stone Features of Challenges Good

slide-1
SLIDE 1

Research at the Boundary of Robotics and AI: Challenge Problems

Prof: Peter Stone Department of Computer Science The University of Texas at Austin

slide-2
SLIDE 2

Features of Challenges

  • Good performance metrics

Peter Stone

slide-3
SLIDE 3

Features of Challenges

  • Good performance metrics
  • Lead to data sets

Peter Stone

slide-4
SLIDE 4

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

Peter Stone

slide-5
SLIDE 5

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect

Peter Stone

slide-6
SLIDE 6

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect
  • Standard platform, software

Peter Stone

slide-7
SLIDE 7

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect
  • Standard platform, software

− Build on platforms and domains that are already working robustly

Peter Stone

slide-8
SLIDE 8

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect
  • Standard platform, software

− Build on platforms and domains that are already working robustly − Also can stick us in local minimum

Peter Stone

slide-9
SLIDE 9

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect
  • Standard platform, software

− Build on platforms and domains that are already working robustly − Also can stick us in local minimum

  • Something that people actually want done

Peter Stone

slide-10
SLIDE 10

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect
  • Standard platform, software

− Build on platforms and domains that are already working robustly − Also can stick us in local minimum

  • Something that people actually want done
  • Learning

Peter Stone

slide-11
SLIDE 11

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect
  • Standard platform, software

− Build on platforms and domains that are already working robustly − Also can stick us in local minimum

  • Something that people actually want done
  • Learning

− Commonsense knowledge from humans and/or big data

Peter Stone

slide-12
SLIDE 12

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect
  • Standard platform, software

− Build on platforms and domains that are already working robustly − Also can stick us in local minimum

  • Something that people actually want done
  • Learning

− Commonsense knowledge from humans and/or big data

  • Detect and adjust to human preferences

Peter Stone

slide-13
SLIDE 13

Features of Challenges

  • Good performance metrics
  • Lead to data sets

− Tension between data sets and embodiment/interactivity

  • Open world aspect, real-time aspect
  • Standard platform, software

− Build on platforms and domains that are already working robustly − Also can stick us in local minimum

  • Something that people actually want done
  • Learning

− Commonsense knowledge from humans and/or big data

  • Detect and adjust to human preferences
  • Push state of the arts both in robotics and in AI

Peter Stone

slide-14
SLIDE 14

Challenges

  • Robot scavenger hunt (Amazing Race)

Peter Stone

slide-15
SLIDE 15

Challenges

  • Robot scavenger hunt (Amazing Race)
  • Human-robot interaction for assembly

Peter Stone

slide-16
SLIDE 16

Challenges

  • Robot scavenger hunt (Amazing Race)
  • Human-robot interaction for assembly

− Intent/activity recognition

Peter Stone

slide-17
SLIDE 17

Challenges

  • Robot scavenger hunt (Amazing Race)
  • Human-robot interaction for assembly

− Intent/activity recognition

  • RoboCup with 4 robots and 1 person

Peter Stone

slide-18
SLIDE 18

Challenges

  • Robot scavenger hunt (Amazing Race)
  • Human-robot interaction for assembly

− Intent/activity recognition

  • RoboCup with 4 robots and 1 person
  • Adjustable autonomy wheelchair

Peter Stone

slide-19
SLIDE 19

Challenges

  • Robot scavenger hunt (Amazing Race)
  • Human-robot interaction for assembly

− Intent/activity recognition

  • RoboCup with 4 robots and 1 person
  • Adjustable autonomy wheelchair
  • Device disassembly

Peter Stone

slide-20
SLIDE 20

Challenges

  • Robot scavenger hunt (Amazing Race)
  • Human-robot interaction for assembly

− Intent/activity recognition

  • RoboCup with 4 robots and 1 person
  • Adjustable autonomy wheelchair
  • Device disassembly
  • Kitchen and household tasks

Peter Stone