Accurate kinodynamic models play a crucial role in many robotics applications such as off-road navigation and high-speed driving. Many state-of-the-art approaches in learning stochastic kinodynamic models, however, require precise measurements of robot states as labeled input/output examples, which can be hard to obtain in outdoor settings due to limited sensor capabilities and the absence of ground truth. In this work, we propose a new technique for learning neural stochastic kinodynamic models from noisy and indirect observations by performing simultaneous state estimation and dynamics learning. The proposed technique iteratively improves the kinodynamic model in an expectation-maximization loop, where the E Step samples posterior state trajectories using particle filtering, and the M Step updates the dynamics to be more consistent with the sampled trajectories via stochastic gradient ascent. We evaluate our approach on both simulation and real-world benchmarks and compare it with several baseline techniques. Our approach not only achieves significantly higher accuracy but is also more robust to observation noise, thereby showing promise for boosting the performance of many other robotics applications.

翻译：精确的流体动力模型在许多机器人应用中发挥着关键作用,例如越野导航和高速驾驶等。然而,在学习随机运动动力模型方面,许多最先进的方法要求精确测量机器人状态,将其作为标签输入/输出实例,由于传感器能力有限和缺乏地面真理,在户外环境中很难获得这些实例。在这项工作中,我们提出一种新的技术,通过同时进行状态估计和动态学习,从噪音和间接观测中学习神经切片运动动力模型。拟议的技术反复改进了期待最大化循环中的动态动力模型,E Step样本后方状态模型使用粒子过滤,M Step则更新了该动态,以便与抽样轨迹更加一致。我们评估了我们的模拟和真实世界基准方法,并将它与若干基线技术进行比较。我们的方法不仅实现了显著的准确性,而且对观测噪音也更加有力,从而展示了利用粒子过滤来提升其他机器人应用性能的希望。