UniPoint：面向挑战性地形的仿人机器人统一点级传感器融合
UniPoint: Unified Point-Level Sensor Fusion for Humanoid Locomotion Across Challenging Terrains
浏览论文内容
中文总结 AI 辅助
针对仿人机器人复杂地形感知的覆盖、精度与冗余难题，提出基于360°激光雷达和双深度相机点级早期融合的UniPoint框架，以固定令牌编码解耦成本，单次训练生成八种地形的统一策略，并在DR02上验证了跨场景鲁棒性。
中文摘要 AI 辅助
开放世界部署要求仿人机器人在高度异质的地形上安全行走，其感知需同时提供宽覆盖、局部精度以及对传感器故障的冗余。现有方法难以同时满足这三个要求：单个前向深度相机或近处高度采样覆盖范围过小；经里程计校正的高程图在剧烈运动下会漂移，并会遗漏细薄的垂直结构；图像级编码的成本随相机数量增长。我们提出UniPoint，一个基于多源点级传感器融合的仿人全身运动框架。来自360°激光雷达（LiDAR）和两个深度相机的测量被早期融合为一个基坐标系点集。体素化将其重采样为固定数量的令牌，由线性自注意力和本体感觉查询的交叉注意力编码，使前向计算成本与传感器数量解耦。该点集保留站立的细薄障碍物；单一模态故障仅移除部分令牌，因此策略可优雅降级。通过一次包含地形感知奖励、感知退化注入和域随机化的训练运行，即可为所有八种地形类型生成一个策略，并部署在板载RK3588上，无需微调。在DR02仿人机器人上，于七种地形类型的九个真实世界场景中各进行20次试验，验证了该策略在70厘米高平台、100厘米间隙、细薄障碍物以及稀疏或狭窄落脚点上的表现；它还能零样本泛化到户外环境。
英文摘要
Open-world deployment requires humanoid robots to cross highly heterogeneous terrain safely, with perception that simultaneously provides wide coverage, local accuracy, and redundancy against sensor failure. Existing approaches struggle to satisfy all three: one forward depth camera or nearby height sampling covers too little; odometry-corrected elevation maps drift under aggressive motion and miss thin vertical structures; image-level encoding costs grow with camera count. We present UniPoint, a humanoid whole-body locomotion framework built on multi-source point-level sensor fusion. Measurements from a 360° light detection and ranging (LiDAR) sensor and two depth cameras are early-fused into one base-frame point set. Voxelization resamples it to a fixed number of tokens encoded by linear self-attention and proprioception-queried cross-attention, decoupling forward cost from sensor count. The point set retains standing thin barriers; a single-modality failure removes only part of the tokens, so the policy degrades gracefully. A single training run with terrain-aware rewards, perception-degradation injection, and domain randomization produces one policy for all eight terrain types, deployed on an onboard RK3588 without fine-tuning. On a DR02 humanoid, 20 trials at each of nine real-world settings over seven terrain types validate the policy on 70-cm-high platforms, 100-cm gaps, thin barriers, and sparse or narrow footholds; it also generalizes zero-shot outdoors.
发表机构
- Zhejiang University（浙江大学）
- Yunshenchu Technology Co., Ltd.（云深处科技有限公司）
- Zhejiang Key Laboratory of Additive Manufacturing Technology and Equipment（浙江省增材制造技术与装备重点实验室）
机构由 AI 辅助整理，请以论文原文为准。
