从点云中学习随车辆状态变化的可通行性，提升越野自动驾驶决策效率。
Learning Smooth State-Dependent Traversability from Dense Point Clouds
- 用傅里叶基函数建模角度依赖的可通行风险分布，输出光滑函数。
- 仿真中穿越40米巨石场成功率达91%，比基线高18个百分点。
- 适合需实时规划的无人车系统，尤其在复杂地形场景下。
越野自主导航中的关键挑战在于地形可通行性常依赖于车辆状态，某些障碍物仅从特定朝向可通行。若将接近角度作为模型输入，需大规模多样数据训练，且规划时重复推理计算开销大。为此，我们提出SPARTA方法，从点云估计角度相关的可通行性。通过在网络输出中引入1-球面上的几何结构，以最小开销生成光滑解析函数，可预测任意接近角的风险分布，并支持后续查询复用。该函数由傅里叶基函数构成，因其周期性和平滑性，有利于泛化。我们在高保真仿真平台验证，模型穿越40米巨石场成功率高达91%（基线为73%），并在硬件上展示其在真实场景的泛化能力。代码将开源。
原文摘要 · Abstract (English)
A key open challenge in off-road autonomy is that the traversability of terrain often depends on the vehicle's state. In particular, some obstacles are only traversable from some orientations. However, learning this interaction by encoding the angle of approach as a model input demands a large and diverse training dataset and is computationally inefficient during planning due to repeated model inference. To address these challenges, we present SPARTA, a method for estimating approach angle conditioned traversability from point clouds. Specifically, we impose geometric structure into our network by outputting a smooth analytical function over the 1-Sphere that predicts risk distribution for any angle of approach with minimal overhead and can be reused for subsequent queries. The function is composed of Fourier basis functions, which has important advantages for generalization due to their periodic nature and smoothness. We demonstrate SPARTA both in a high-fidelity simulation platform, where our model achieves a 91\% success rate crossing a 40m boulder field (compared to 73\% for the baseline), and on hardware, illustrating the generalization ability of the model to real-world settings. Our code will be available at https://github.com/neu-autonomy/SPARTA.
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。