Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projection
Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projection
复制标题
DOI：
10.48550/arxiv.2205.04667
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Thomas Power;D. Berenson
中科院分区：
文献类型：
--
作者：
Thomas Power;D. Berenson
我们提出一种用于无碰撞导航的模型预测控制（MPC）方法，该方法使用摊销变分推理，通过训练一个以起点、目标和环境为条件的归一化流来近似最优控制序列的分布。这种表示方式使我们能够学习一种既考虑机器人动力学又考虑复杂障碍物几何形状的分布。然后，我们可以从该分布中采样以生成控制序列，这些控制序列作为我们提出的基于FlowMPPI采样的MPC方法的一部分，很可能既指向目标又无碰撞。然而，在部署该方法时，机器人可能会遇到分布外（OOD）环境，即与训练中使用的环境完全不同的环境。在这种情况下，不能信赖所学习的流能够生成低成本的控制序列。为了将我们的方法推广到OOD环境，我们还提出一种在MPC过程中对环境表示进行投影的方法。这种投影将环境表示改变得更接近分布内，同时还优化真实环境中的轨迹质量。我们在二维双积分器和三维12自由度欠驱动四旋翼上的模拟结果表明，带有投影的FlowMPPI在分布内和OOD环境中都优于最先进的MPC基准，包括从真实世界数据生成的OOD环境。
We propose a Model Predictive Control (MPC) method for collision-free navigation that uses amortized variational inference to approximate the distribution of optimal control sequences by training a normalizing flow conditioned on the start, goal and environment. This representation allows us to learn a distribution that accounts for both the dynamics of the robot and complex obstacle geometries. We can then sample from this distribution to produce control sequences which are likely to be both goal-directed and collision-free as part of our proposed FlowMPPI sampling-based MPC method. However, when deploying this method, the robot may encounter an out-of-distribution (OOD) environment, i.e. one which is radically different from those used in training. In such cases, the learned flow cannot be trusted to produce low-cost control sequences. To generalize our method to OOD environments we also present an approach that performs projection on the representation of the environment as part of the MPC process. This projection changes the environment representation to be more in-distribution while also optimizing trajectory quality in the true environment. Our simulation results on a 2D double-integrator and a 3D 12DoF underactuated quadrotor suggest that FlowMPPI with projection outperforms state-of-the-art MPC baselines on both in-distribution and OOD environments, including OOD environments generated from real-world data.