ai and robotics
play

AI and Robotics Wheeler Ruml Department of Computer Science - PowerPoint PPT Presentation

AI and Robotics Wheeler Ruml Department of Computer Science www.cs.unh.edu/~ruml Wheeler Ruml (UNH) AI and Robotics 1 / 5 Research Planning: ideas from combinatorial search Research Integration canon (Robin): models (abstraction)


  1. AI and Robotics Wheeler Ruml Department of Computer Science www.cs.unh.edu/~ruml Wheeler Ruml (UNH) AI and Robotics – 1 / 5

  2. Research Planning: ideas from combinatorial search ■ Research ■ Integration canon (Robin): models (abstraction) + inference (search) ■ ■ Challenges abstraction-based guidance ■ suboptimal search (bounded, contract, utility-based) ■ real-time planning, concurrent execution (Manuela) ■ multi-level planning (Max, Dawn): hierarchical search ■ Wheeler Ruml (UNH) AI and Robotics – 2 / 5

  3. Research Planning: ideas from combinatorial search ■ Research ■ Integration canon (Robin): models (abstraction) + inference (search) ■ ■ Challenges abstraction-based guidance ■ suboptimal search (bounded, contract, utility-based) ■ real-time planning, concurrent execution (Manuela) ■ multi-level planning (Max, Dawn): hierarchical search ■ Perception: focus of attention, ‘purposeful’ (Jana, Manuela, Matthias) ■ Wheeler Ruml (UNH) AI and Robotics – 2 / 5

  4. Encouraging Integration Funders: ■ Research ■ Integration fund workshop invited speakers ■ ■ Challenges fund presentation of journal papers at related conferences ■ fund workshops that rotate among conferences ■ fund summer school or workshop (Robin) ■ how to encourage publishing in diverse venues? ■ Wheeler Ruml (UNH) AI and Robotics – 3 / 5

  5. Encouraging Integration Funders: ■ Research ■ Integration fund workshop invited speakers ■ ■ Challenges fund presentation of journal papers at related conferences ■ fund workshops that rotate among conferences ■ fund summer school or workshop (Robin) ■ how to encourage publishing in diverse venues? ■ Event organizers: umbrella model: present best papers from related ■ conferences, ‘what’s hot’ talks clearly demarcate outreach from research events, invite ■ organizers to report out on current technical approaches and challenges ( not co-location: too hard ) ■ Wheeler Ruml (UNH) AI and Robotics – 3 / 5

  6. Challenge Problems cheap reliable common platform (UBR-1) ■ ■ Research works in simulation ■ Integration ■ ■ Challenges min ∆ ‘shaping’. eg: Physical TSP, setting the table ■ ask people with jobs, money, cool factor ( ≈ David E. Smith) ■ counter-balance with explicit encouragement of exploratory ■ research on new problem settings (Tomas) Wheeler Ruml (UNH) AI and Robotics – 4 / 5

Recommend


More recommend