PoCo: Policy Composition from and for Heterogeneous Robot Learning
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:RXIAQLMUrecord.jsonopen to challenge →
read the original abstract
Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile, and proprioceptive information, and collected in different domains such as simulation, real robots, and human videos. Current methods usually collect and pool all data from one domain to train a single policy to handle such heterogeneity in tasks and domains, which is prohibitively expensive and difficult. In this work, we present a flexible approach, dubbed Policy Composition, to combine information across such diverse modalities and domains for learning scene-level and task-level generalized manipulation skills, by composing different data distributions represented with diffusion models. Our method can use task-level composition for multi-task manipulation and be composed with analytic cost functions to adapt policy behaviors at inference time. We train our method on simulation, human, and real robot data and evaluate in tool-use tasks. The composed policy achieves robust and dexterous performance under varying scenes and tasks and outperforms baselines from a single data source in both simulation and real-world experiments. See https://liruiw.github.io/policycomp for more details .
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
Energy-based Compositional Diffusion Planning
ECD reformulates compositional diffusion planning as energy minimization over local bridge potentials, adding a boundary reaction term and a Markov score approximation that runs in linear time.
-
Multi-Modal Manipulation via Multi-Modal Policy Consensus
A policy that factorizes into modality-specific diffusion models combined by a learned router network for adaptive multi-modal robotic manipulation.
-
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
DSRL steers pretrained diffusion policies for robotics by applying RL to their latent noise inputs, achieving sample-efficient real-world adaptation with only black-box access.
-
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
DeLock mitigates lock-in in low-data VLA post-training via visual grounding preservation and test-time contrastive prompt guidance, outperforming baselines across eight evaluations while matching data-heavy generalist...
-
DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
DexVLA combines a scaled diffusion action expert with embodiment curriculum learning to achieve better generalization and performance than prior VLA models on diverse robot hardware and long-horizon tasks.
-
Diffusion Policy Policy Optimization
DPPO fine-tunes diffusion policies via policy gradients and outperforms prior RL approaches for diffusion policies and PG-tuned alternatives on robot benchmarks while enabling stable training and hardware deployment.
-
IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation
IMPACT decouples forceful manipulation into task-planning and internal-model predictive control, claiming higher success rates, better generalization to unseen weights, and improved safety and energy efficiency in sim...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.