Robix: A Unified Model for Robot Interaction, Reasoning and Planning
This addresses the challenge of creating more capable and user-friendly robots for applications like table bussing and grocery shopping, though it appears incremental as it builds on existing vision-language and reasoning methods.
The paper tackles the problem of enabling robots to handle complex instructions, plan tasks, and interact naturally with humans by introducing Robix, a unified model that integrates reasoning, planning, and interaction within a single vision-language architecture, and it outperforms baselines like GPT-4o and Gemini 2.5 Pro in interactive task execution across diverse instruction types and tasks.
We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive layer in a hierarchical robot system, Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction, enabling robots to follow complex instructions, plan long-horizon tasks, and interact naturally with human within an end-to-end framework. Robix further introduces novel capabilities such as proactive dialogue, real-time interruption handling, and context-aware commonsense reasoning during task execution. At its core, Robix leverages chain-of-thought reasoning and adopts a three-stage training strategy: (1) continued pretraining to enhance foundational embodied reasoning abilities including 3D spatial understanding, visual grounding, and task-centric reasoning; (2) supervised finetuning to model human-robot interaction and task planning as a unified reasoning-action sequence; and (3) reinforcement learning to improve reasoning-action consistency and long-horizon task coherence. Extensive experiments demonstrate that Robix outperforms both open-source and commercial baselines (e.g., GPT-4o and Gemini 2.5 Pro) in interactive task execution, demonstrating strong generalization across diverse instruction types (e.g., open-ended, multi-stage, constrained, invalid, and interrupted) and various user-involved tasks such as table bussing, grocery shopping, and dietary filtering.