REVIEW 4 cited by
Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real
read the original abstract
Manipulation and locomotion are closely related problems that are often studied in isolation. In this work, we study the problem of coordinating multiple mobile agents to exhibit manipulation behaviors using a reinforcement learning (RL) approach. Our method hinges on the use of hierarchical sim2real -- a simulated environment is used to learn low-level goal-reaching skills, which are then used as the action space for a high-level RL controller, also trained in simulation. The full hierarchical policy is then transferred to the real world in a zero-shot fashion. The application of domain randomization during training enables the learned behaviors to generalize to real-world settings, while the use of hierarchy provides a modular paradigm for learning and transferring increasingly complex behaviors. We evaluate our method on a number of real-world tasks, including coordinated object manipulation in a multi-agent setting. See videos at https://sites.google.com/view/manipulation-via-locomotion
Forward citations
Cited by 4 Pith papers
-
S3: Stable Subgoal Selection by Constraining Uncertainty of Coarse Dynamics in Hierarchical Reinforcement Learning
S3 adds a high-level intrinsic reward that penalizes the predicted variance of coarse multi-step subgoal outcomes, improving HRL performance on bottleneck-heavy MuJoCo tasks.
-
LAMP: Long-Horizon Adaptive Manipulation Planning for Multi-Robot Collaboration in Cluttered Space
LAMP couples learned short-horizon multi-robot pushing with A* and lazy D* Lite search so object paths stay robot-feasible in dense clutter and replan under drift.
-
Abstract Sim2Real through Approximate Information States
Abstract simulators can be grounded to real tasks by making their dynamics history-dependent and correcting them with real data, enabling RL policy transfer.
-
LAMP: Long-Horizon Adaptive Manipulation Planning for Multi-Robot Collaboration in Cluttered Space
LAMP combines a learned generative manipulation model with LAMPA* systematic search and LAMP-Lazy deferred-evaluation planning to solve long-horizon multi-robot tasks in cluttered environments that prior methods canno...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.