StereoPolicy：通过立体视觉改进机器人操作策略
StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception
AI总结：
该研究提出StereoPolicy，一种利用立体视觉提升机器人操作策略的框架，通过同步立体图像对增强几何推理，无需构建显式3D表示，在多个仿真和真实机器人任务中优于RGB、RGB-D、点云等基线方法。
摘要：
最近的机器人模仿学习进展产生了能够从视觉输入中操控多样化物体的强大视觉-运动策略。然而，单目观测缺乏深度信息，这对于在杂乱或几何复杂的场景中进行精确操作至关重要。显式的深度图和点云在现实世界操作中往往噪声大且易碎。我们引入了StereoPolicy，一种视觉-运动策略学习框架，直接利用同步的立体图像对来改进几何推理，而无需构建显式的3D表示。StereoPolicy通过预训练的2D视觉编码器处理每张图像，并通过基于交叉注意力的Stereo Transformer融合左右特征，隐式地捕捉空间对应关系和视差线索。该框架与基于扩散和预训练的视觉-语言-动作（VLA）策略集成，在三个仿真基准和七个真实机器人桌面和双臂移动操作任务中，相比RGB、RGB-D、点云和多视角基线方法均实现了持续改进。我们的结果表明，立体视觉能够将预训练的2D表示与3D几何理解联系起来，以提升机器人操作性能。
英文摘要：
Recent advances in robot imitation learning have produced powerful visuomotor policies that manipulate diverse objects from visual inputs. However, monocular observations lack depth information, which is critical for precise manipulation in cluttered or geometrically complex scenes. Explicit depth maps and point clouds are often noisy and fragile in real-world manipulation. We introduce StereoPolicy, a visuomotor policy learning framework that directly leverages synchronized stereo image pairs to improve spatial perception without constructing explicit 3D representations. StereoPolicy processes each image with pretrained 2D vision encoders and fuses left-right features through a cross-attention-based Stereo Transformer, learning task-conditioned binocular representations. The framework integrates with diffusion-based and pretrained vision-language-action (VLA) policies, delivering consistent improvements over RGB, RGB-D, point cloud, and multi-view baselines across three simulation benchmarks and seven real-robot tabletop and bimanual mobile manipulation tasks. Our results support task-trained binocular fusion as an effective way to adapt 2D visual representations for manipulation.
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。
