Model-based autonomous system for performing dexterous, human-level manipulation tasks
Author(s)Hudson, Nicolas; Ma, Jeremy; Hebert, Paul; Jain, Abhinandan; Bajracharya, Max; Allen, Thomas; Sharan, Rangoli; Horowitz, Matanya; Kuo, Calvin; Matthies, Larry; Backes, Paul; Burdick, Joel; Howard, Thomas M.; ... Show more Show less
MetadataShow full item record
This article presents a model based approach to autonomous dexterous manipulation, developed as part of the DARPA Autonomous Robotic Manipulation Software (ARM-S) program. Performing human-level manipulation tasks is achieved through a novel combination of perception in uncertain environments, precise tool use, forceful dual-arm planning and control, persistent environmental tracking, and task level verification. Deliberate interaction with the environment is incorporated into planning and control strategies, which, when coupled with world estimation, allows for refinement of models and precise manipulation. The system takes advantage of sensory feedback immediately with little open-loop execution, attempting true autonomous reasoning and multi-step sequencing that adapts in the face of changing and uncertain environments. A tire change scenario utilizing human tools, discussed throughout the article, is used to described the system approach. A second scenario of cutting a wire is also presented, and is used to illustrate system component reuse and generality.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Hudson, Nicolas et al. “Model-Based Autonomous System for Performing Dexterous, Human-Level Manipulation Tasks.” Autonomous Robots 36.1–2 (2014): 31–49.
Author's final manuscript