We propose a novel approach to multi-robot collaboration that harnesses the power of pre-trained large language models (LLMs) for both high-level communication and low-level path planning. Robots are equipped with LLMs to discuss and collectively reason task strategies. They generate sub-task plans and task space waypoint paths, which are used by a multi-arm motion planner to accelerate trajectory planning. We also provide feedback from the environment, such as collision checking, and prompt the LLM agents to improve their plan and waypoints in-context. For evaluation, we introduce RoCoBench, a 6-task benchmark covering a wide range of multi-robot collaboration scenarios, accompanied by a text-only dataset that evaluates LLMs’ agent representation and reasoning capability. We experimentally demonstrate the effectiveness of our approach — it achieves high success rates across all tasks in RoCoBench and adapts to variations in task semantics. Our dialog setup offers high interpretability and flexibility — in real world experiments, we show RoCo easily incorporates human-in-the-loop, where a user can communicate and collaborate with a robot agent to complete tasks together.

We present a prototype virtual reality user interface for robot teleoperation that supports high-level specification of 3D object positions and orientations in remote assembly tasks. Users interact with virtual replicas of task objects. They asynchronously assign multiple goals in the form of 6DoF destination poses without needing to be familiar with specific robots and their capabilities, and manage and monitor the execution of these goals. The user interface employs two different spatiotemporal visualizations for assigned goals: one represents all goals within the user’s workspace (Aggregated View), while the other depicts each goal within a separate world in miniature (Timeline View). We conducted a user study of the interface without the robot system to compare how these visualizations affect user efficiency and task load. The results show that while the Aggregated View helped the participants finish the task faster, the participants preferred the Timeline View.

We introduce a practical robotics solution for the task of heterogeneous bagging, requiring the placement of multiple rigid and deformable objects into a deformable bag. This is a difficult task as it features complex interactions between multiple highly deformable objects under limited observability. To tackle these challenges, we propose a robotic system consisting of two learned policies: a rearrangement policy that learns to place multiple rigid objects and fold deformable objects in order to achieve desirable pre-bagging conditions, and a lifting policy to infer suitable grasp points for bi-manual bag lifting. We evaluate these learned policies on a real-world three-arm robot platform that achieves a 70% heterogeneous bagging success rate with novel objects. To facilitate future research and comparison, we also develop a novel heterogeneous bagging simulation benchmark that will be made publicly available.