通过消除重复推理，让机器人在本地高效决策
On-Device Robotic Planning: Eliminating Inference Redundancy for Efficient Decision-Making
- 借鉴人类认知，用轻量门控与路由机制减少冗余计算
- 在ALFRED和真实机器人任务中推理延迟降低，性能保持竞争力
- 适合需要低延迟实时决策的嵌入式机器人系统
基于大语言模型和视觉-语言模型的推理型机器人策略虽具备强大的语义规划能力，但普遍存在高推理延迟问题，限制了实际实时部署。本文观察到机器人推理任务中存在显著的时间冗余：连续观测常产生相同动作与子目标。基于此，提出受人类认知启发的REIS框架，通过轻量级场景门控、KV驱动的可用性路由与深思熟虑的推理机制，在满足具身约束条件下加速机器人控制。在ALFRED及真实机器人任务上的实验表明，REIS显著降低了推理开销，同时保持了具有竞争力的任务表现。
原文摘要 · Abstract (English)
Reasoning-based robotic policies using large language and vision-language models achieve strong semantic planning capabilities but mostly suffer from a high inference latency that limits practical real-time deployment. In this work, we observe that robotic reasoning workloads contain substantial temporal redundancy, where consecutive observations frequently produce identical actions and subgoals. Based on this insight, we present REIS, a human cognition inspired robotic decision-making framework that minimizes unnecessary reasoning while preserving semantic adaptability. REIS combines lightweight scene gating, KV-steered affordance routing, and deliberative reasoning to accelerate robotic control under embodied constraints. Experiments on ALFRED, and real-world robotic tasks demonstrate that REIS significantly suppresses reasoning overhead while maintaining competitive task performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。