MATS: An Interpretable Trajectory Forecasting Representation for Planning and Control
MATS: An Interpretable Trajectory Forecasting Representation for Planning and Control
复制标题
DOI：
--
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
B. Ivanovic;Amine Elhafsi;G. Rosman;Adrien Gaidon;M. Pavone
中科院分区：
文献类型：
--
作者：
B. Ivanovic;Amine Elhafsi;G. Rosman;Adrien Gaidon;M. Pavone
人体运动推理是现代人机交互系统的核心组成部分。特别是，行为预测在自主系统中的主要用途之一是通知自我机器人运动规划和控制。然而，大多数规划和控制算法的原因是系统动力学，而不是预测的代理轨迹，通常是由轨迹预测方法，这可能会阻碍他们的集成输出。为此，我们提出仿射时变系统（MATS）的混合物作为输出表示的轨迹预测，更适合下游规划和控制使用。我们的方法利用成功的想法，从概率轨迹预测工程学习动力系统表示，在规划和控制文献中得到充分研究。我们将我们的预测与建议的多模态规划方法相结合，并在大规模自动驾驶数据集上展示了显着的计算效率改进。
Reasoning about human motion is a core component of modern human-robot interactive systems. In particular, one of the main uses of behavior prediction in autonomous systems is to inform ego-robot motion planning and control. However, a majority of planning and control algorithms reason about system dynamics rather than the predicted agent tracklets that are commonly output by trajectory forecasting methods, which can hinder their integration. Towards this end, we propose Mixtures of Affine Time-varying Systems (MATS) as an output representation for trajectory forecasting that is more amenable to downstream planning and control use. Our approach leverages successful ideas from probabilistic trajectory forecasting works to learn dynamical system representations that are well-studied in the planning and control literature. We integrate our predictions with a proposed multimodal planning methodology and demonstrate significant computational efficiency improvements on a large-scale autonomous driving dataset.