From Robotic Systems to Robotics-grounded AI Systems Maxim - PowerPoint PPT Presentation

From Robotic Systems to Robotics-grounded AI Systems Maxim Likhachev Robotics Institute & NREC Carnegie Mellon University

Transitioning Robotics Systems into the Real World Lots of progress in the last decade, with various robotics systems being transitioned into the real world… Urban Challenge’07 CMU efforts joint project with Lockheed Martin joint work with Stentz, Kelly, etc. at NREC Maxim Likhachev Carnegie Mellon University 2

Transitioning Robotics Systems into the Real World Lots of progress in the last decade, with various robotics systems being transitioned into the real world… Urban Challenge’07 CMU efforts All are well-done Robotics Systems, All are well-done Robotics Systems, with no real AI in them! with no real AI in them! joint project with Lockheed Martin joint work with Stentz, Kelly, etc. at NREC Maxim Likhachev Carnegie Mellon University 3

Typical Robotics Architecture Execution Monitor Maxim Likhachev Carnegie Mellon University 4

Typical Robotics Architecture Execution Monitor All modules are engineered for expected All modules are engineered for expected conditions and fail under unexpected conditions conditions and fail under unexpected conditions Maxim Likhachev Carnegie Mellon University 5

Typical Robotics Architecture Execution Monitor All modules are engineered for expected All modules are engineered for expected conditions and fail under unexpected conditions conditions and fail under unexpected conditions Robotics-grounded AI : Robotics-grounded AI : Need to research how to introduce a deeper Need to research how to introduce a deeper understanding of the world and the robot itself understanding of the world and the robot itself In Planning/Decision-making: In Planning/Decision-making: need better ways to represent knowledge about need better ways to represent knowledge about the world and the robot itself, need to learn the world and the robot itself, need to learn from experience and demonstrations, need to from experience and demonstrations, need to reason about its own capabilities, … reason about its own capabilities, … Maxim Likhachev Carnegie Mellon University 6

Example I: Planning for Manipulation Planning Representations Have to Be Dynamic - we can’t model all potentially relevant factors in the real -world - planner needs to figure out what, when and how it should model - introduce “necessary” dimensions as part of planning - learn relevant dimensions based on experience - learn how to model environment from demonstrations Experience Graphs: planning with learning from experience and demonstrations [Phillips et al., RSS’13, ’12] Maxim Likhachev Carnegie Mellon University 7

Example II: Planning for Aerial Vehicles Planning Needs to Be Reason about the Models of Other Modules - perception is brittle, controls are imperfect, localization is noisy,… - planner needs to reason about strengths/weaknesses of these modules State Lattice with Controllers [Butzke et al., IROS’14] Maxim Likhachev Carnegie Mellon University 8

Challenge Problem General Purpose Mobile Manipulators for Manufacturing - semi-structured environments but still plenty of uncertainty - tasks require modeling object behavior and often dynamics - potentially high impact on economy - many aspects can be simulated - common open software infrastructure exists, thanks to ROS! Maxim Likhachev Carnegie Mellon University 9