Corpus ID: 237048121

Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration

  title={Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration},
  author={Chen Wang and Claudia P'erez-D'Arpino and Danfei Xu and Li Fei-Fei and C. Karen Liu and Silvio Savarese},
We present a method for learning a human-robot collaboration policy from human-human collaboration demonstrations. An effective robot assistant must learn to handle diverse human behaviors shown in the demonstrations and be robust when the humans adjust their strategies during online task execution. Our method co-optimizes a human policy and a robot policy in an interactive learning process: the human policy learns to generate diverse and plausible collaborative behaviors from demonstrations… Expand

Figures and Tables from this paper


Efficient Model Learning from Joint-Action Demonstrations for Human-Robot Collaborative Tasks
Results indicate that learning human user models from joint-action demonstrations and encoding them in a MOMDP formalism can support effective teaming in human-robot collaborative tasks. Expand
A system for learning continuous human-robot interactions from human-human demonstrations
The effectiveness of the data-driven imitation learning system for learning human-robot interactions from human-human demonstrations on complex, sequential tasks is shown by presenting two applications involving collaborative human- robot assembly. Expand
A survey of robot learning from demonstrations for Human-Robot Collaboration
A survey of recent research in robot learning from demonstration (LfD) while focusing on studies for human-robot collaborative tasks, and some recent works that focus on designing better communication channels/methods are reviewed. Expand
Decision-Making for Bidirectional Communication in Sequential Human-Robot Collaborative Tasks
This work presents a computational framework that decides if, when, and what to communicate during human-robot collaboration, and implements CommPlan for a shared workspace task, in which the robot has multiple communication options and needs to reason within a short time. Expand
Learning Latent Representations to Influence Multi-Agent Interaction
This work proposes a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy and leverages these latent dynamics to influence the otherAgent, purposely guiding them towards policies suitable for co-adaptation. Expand
Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification
A data-driven approach that synthesizes anticipatory knowledge of both human motions and subsequent action steps in order to predict in real-time the intended target of a human performing a reaching motion is presented. Expand
Probabilistic movement modeling for intention inference in human–robot interaction
The Intention-Driven Dynamics Model is proposed to probabilistically model the generative process of movements that are directed by the intention and allows the intention to be inferred from observed movements using Bayes’ theorem. Expand
Efficient Bimanual Manipulation Using Learned Task Schemas
It is shown that explicitly modeling the schema’s state-independence can yield significant improvements in sample efficiency for model-free reinforcement learning algorithms and can be transferred to solve related tasks, by simply re-learning the parameterizations with which the skills are invoked. Expand
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
The novel task FurnMove is introduced, in which agents work together to move a piece of furniture through a living room to a goal, and SYNC-policies (synchronize your actions coherently) and CORDIAL (coordination loss) are introduced. Expand
Learning Multi-Arm Manipulation Through Collaborative Teleoperation
Multi-Arm RoboTurk (MART), a multi-user data collection platform that allows multiple remote users to simultaneously teleoperate a set of robotic arms and collect demonstrations for multi-arm tasks, is presented and a base-residual policy framework is proposed that allows trained policies to better adapt to the mixed coordination setting common in multi- arm manipulation. Expand