Two papers accepted at Conference on Robot Learning (CoRL) 2025 | SLMC

27-30 September 2025 Seoul, Korea

Andreas Sochopoulos, Nikolay Malkin, Nikolaos Tsagkas, Joao Moura, Michael Gienger, and Sethu Vijayakumar, Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings, Proc. Conference on Robot Learning (CoRL 2025), Seoul, Korea (2025). [pdf] [video] [citation]

Abstract: Diffusion and flow matching policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. However, their computationally expensive inference, due to the numerical integration of an ODE or SDE, limits their applicability as real-time controllers for robots. We introduce a methodology that utilizes conditional Optimal Transport couplings between noise and samples to enforce straight solutions in the flow ODE for robot action generation tasks. We show that naively coupling noise and samples fails in conditional tasks and propose incorporating condition variables into the coupling process to improve few-step performance. The proposed few-step policy achieves a 4% higher success rate with a 10× speed-up compared to Diffusion Policy on a diverse set of simulation tasks. Moreover, it produces high-quality and diverse action trajectories within 1–2 steps on a set of real-world robot tasks. Our method also retains the same training complexity as Diffusion Policy and vanilla Flow Matching, in contrast to distillation-based approaches.

Marina Aoyama, Joao Moura, Juan Del Aguila Ferrandis, and Sethu Vijayakumar, Poke and Strike: Learning Task-Informed Exploration Policies, Proc. Conference on Robot Learning (CoRL 2025), Seoul, Korea (2025). [pdf] [video] [citation]

Abstact: In many dynamic robotic tasks, such as striking pucks into a goal outside the reachable workspace, the robot must first identify the relevant physical properties of the object for successful task execution, as it is unable to recover from failure or retry without human intervention. To address this challenge, we propose a task-informed exploration approach, based on reinforcement learning, that trains an exploration policy using rewards automatically generated from the sensitivity of a privileged task policy to errors in estimated properties. We also introduce an uncertainty-based mechanism to determine when to transition from exploration to task execution, ensuring sufficient property estimation accuracy with minimal exploration time. Our method achieves a 90% success rate on the striking task with an average exploration time under 1.2 seconds—significantly outperforming baselines that achieve at most 40% success or require inefficient querying and retraining in a simulator at test time. Additionally, we demonstrate that our task-informed exploration rewards capture the relative importance of physical properties in two manipulation tasks and the classical CartPole example. Finally, we validate our approach by demonstrating its ability to identify object properties and adjust task execution in a physical setup using the KUKA iiwa robot arm. The project website is available at marina-aoyama.github.io/poke-and-strike/.

Accepted workshop papers

Wanming Yu, Adrian Röfer, Abhinav Valada and Sethu Vijayakumar Preference-Based Long-Horizon Robotic Stacking with Multimodal Large Language Models Learning Effective Abstractions for Planning (LEAP)

This article was published on 2025-09-01