机器人抓取中的障碍物推理
Obstruction reasoning for robotic grasping
AI总结：
UNOGrasp通过视觉-语言模型提升机器人抓取中障碍物推理能力，结合监督与强化学习微调，实现更高效的路径规划和抓取性能。
摘要：
在杂乱环境中实现成功的机器人抓取不仅需要一个能够视觉地定位目标物体的模型，还需要能够推理出必须事先清除的障碍物。尽管当前的视觉-语言具身推理模型表现出涌现的空间理解能力，但在障碍物推理和可达性规划方面仍然有限。为弥补这一差距，我们提出了UNOGrasp，一个基于学习的视觉-语言模型，能够执行视觉引导的障碍物推理，以推断出清除路径和抓取目标物体所需的操作序列。我们设计了一种基于目标物体起源的障碍路径的多步骤推理过程。我们通过障碍物感知的视觉线索来锚定每个推理步骤，以激励推理能力。UNOGrasp通过可验证的推理奖励结合监督学习和强化学习微调。此外，我们构建了UNOBench，一个大规模数据集，基于MetaGraspNetV2，包含超过10万条由人类标注的障碍路径，标注了障碍比率、接触点和自然语言指令。广泛的实验和真实机器人评估显示，UNOGrasp在合成和真实环境中显著提高了障碍物推理和抓取成功率，优于通用和专有方法。项目网站：https://tev-fbk.github.io/UnoGrasp/。
英文摘要：
Successful robotic grasping in cluttered environments not only requires a model to visually ground a target object but also to reason about obstructions that must be cleared beforehand. While current vision-language embodied reasoning models show emergent spatial understanding, they remain limited in terms of obstruction reasoning and accessibility planning. To bridge this gap, we present UNOGrasp, a learning-based vision-language model capable of performing visually-grounded obstruction reasoning to infer the sequence of actions needed to unobstruct the path and grasp the target object. We devise a novel multi-step reasoning process based on obstruction paths originated by the target object. We anchor each reasoning step with obstruction-aware visual cues to incentivize reasoning capability. UNOGrasp combines supervised and reinforcement finetuning through verifiable reasoning rewards. Moreover, we construct UNOBench, a large-scale dataset for both training and benchmarking, based on MetaGraspNetV2, with over 100k obstruction paths annotated by humans with obstruction ratios, contact points, and natural-language instructions. Extensive experiments and real-robot evaluations show that UNOGrasp significantly improves obstruction reasoning and grasp success across both synthetic and real-world environments, outperforming generalist and proprietary alternatives. Project website: https://tev-fbk.github.io/UnoGrasp/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
