Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

RE4: Transformation-aware Imitation of Object Interactions Using Manipulation Modes

About

Object interaction tasks have been a focus of advances in imitation learning. End-to-end methods, dominated by diffusion and flow-based variants have shown leaps in performance while sacrificing interpretability. Object-centric and pose-informed variants have had a role in learning from demonstration in manipulation tasks. In this paper, we revisit a few modern imitation learning benchmarks for object interactions, with the aim of composing a framework that repurposes principled theories of manipulation, preserving both performance and interpretability. For image observations, lightweight training is proposed for model-free pose estimation of the target object, using self-supervision over the demonstration data available for imitation learning. This information is then used to inform a manipulation mode-aware retrieval of a demonstration, a mode-aware transformation, a replan step that connects to the retrieval point while preserving mode constraints, and finally rolling out the transformed demonstration. These compose four key steps of the proposed RE4 framework, evaluated over state-based and image-based benchmarks in Push-T and Robomimic. An adversarial benchmark that evaluates sparse data regions of image-based Push-T showcases the robustness, further bolstered by indications from low-data regime experiments. The current work shows promise in using simple interpretable building blocks to learn manipulation skills.

Arsh Chawla, Rahul Shome• 2026

Related benchmarks

TaskDatasetResultRank
Robotic ManipulationRobomimic Can
Success Rate98
57
Robotic ManipulationRobomimic Square
Success Rate95
54
Robotic ManipulationRobomimic Lift
Success Rate100
47
Robotic ManipulationPush T
Average Maximum Coverage91.9
12
Push-TPush T
Training Time (min)0.00e+0
8
CanRobomimic Can
Training Time (minutes)0.00e+0
6
LiftRobomimic Lift
Training Time (minutes)0.00e+0
6
SquareRobomimic Square
Training Time (minutes)0.00e+0
6
Showing 8 of 8 rows

Other info

Follow for update