用可微物理层提升机器人越野轨迹预测的泛化能力。
FusionForce: End-to-end Differentiable Neural-Symbolic Layer for Trajectory Prediction
- 结合可学习力预测与可微物理引擎，端到端生成轨迹。
- 每秒生成10^4条轨迹，显著降低仿真到现实的差距。
- 适合用于控制、强化学习等需要快速模拟的场景。
我们提出一种端到端可微的模型，从相机图像和/或激光雷达点云中预测机器人在崎岖非铺装地形上的运动轨迹。该模型融合了可学习的机器人-地形相互作用力预测模块，以及一个基于经典力学约束的神经符号层，从而提升了分布外数据的泛化能力。神经符号层包含一个可微物理引擎，通过查询机器人与地形接触点的受力情况来计算轨迹。由于架构中嵌入了大量几何与物理先验，该模型也可视为以真实传感器数据为条件的可学习物理引擎，每秒可生成10^4条轨迹。我们论证并实证表明，该架构能有效减少仿真到现实的差距，并缓解分布外数据敏感性。其可微性与高速模拟能力使其适用于模型预测控制、轨迹射击、监督与强化学习，或同时定位与地图构建（SLAM）等多种应用。
原文摘要 · Abstract (English)
We propose end-to-end differentiable model that predicts robot trajectories on rough offroad terrain from camera images and/or lidar point clouds. The model integrates a learnable component that predicts robot-terrain interaction forces with a neural-symbolic layer that enforces the laws of classical mechanics and consequently improves generalization on out-of-distribution data. The neural-symbolic layer includes a differentiable physics engine that computes the robot's trajectory by querying these forces at the points of contact with the terrain. As the proposed architecture comprises substantial geometrical and physics priors, the resulting model can also be seen as a learnable physics engine conditioned on real sensor data that delivers $10^4$ trajectories per second. We argue and empirically demonstrate that this architecture reduces the sim-to-real gap and mitigates out-of-distribution sensitivity. The differentiability, in conjunction with the rapid simulation speed, makes the model well-suited for various applications including model predictive control, trajectory shooting, supervised and reinforcement learning, or SLAM.
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。