Litcius/Paper detail

Catch & Carry

Josh Merel, Saran Tunyasuvunakool, Arun Ahuja, Yuval Tassa, Leonard Hasenclever, Vu Pham, Tom Erez, Greg Wayne, Nicolas Heess

2020ACM Transactions on Graphics98 citationsDOIOpen Access PDF

Abstract

We address the longstanding challenge of producing flexible, realistic humanoid character controllers that can perform diverse whole-body tasks involving object interactions. This challenge is central to a variety of fields, from graphics and animation to robotics and motor neuroscience. Our physics-based environment uses realistic actuation and first-person perception - including touch sensors and egocentric vision - with a view to producing active-sensing behaviors (e.g. gaze direction), transferability to real robots, and comparisons to the biology. We develop an integrated neural-network based approach consisting of a motor primitive module, human demonstrations, and an instructed reinforcement learning regime with curricula and task variations. We demonstrate the utility of our approach for several tasks, including goal-conditioned box carrying and ball catching, and we characterize its behavioral robustness. The resulting controllers can be deployed in real-time on a standard PC. 1

Topics & Concepts

Computer scienceArtificial intelligencePhysics engineHuman–computer interactionRobustness (evolution)Character animationRoboticsAnimationRobotReinforcement learningHumanoid robotPerceptionGazeComputer animationComputer graphics (images)GeneChemistryBiochemistryBiologyNeuroscienceHuman Motion and AnimationHuman Pose and Action RecognitionRobot Manipulation and Learning