Robust Forecasting for Robotic Control: A Game-Theoretic Approach

被引:0
作者
Agarwal, Shubhankar [1 ]
Fridovich-Keil, David [2 ]
Chinchali, Sandeep P. [1 ]
机构
[1] Univ Texas Austin, Dept Elect & Comp Engn, Austin, TX 78712 USA
[2] Univ Texas Austin, Dept Aerosp Engn & Engn Mech, Austin, TX 78712 USA
来源
2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA | 2023年
关键词
D O I
10.1109/ICRA48891.2023.10160721
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Modern robots require accurate forecasts to make optimal decisions in the real world. For example, self-driving cars need an accurate forecast of other agents' future actions to plan safe trajectories. Current methods rely heavily on historical time series to accurately predict the future. However, relying entirely on the observed history is problematic since it could be corrupted by noise, have outliers, or not completely represent all possible outcomes. To solve this problem, we propose a novel framework for generating robust forecasts for robotic control. In order to model real-world factors affecting future forecasts, we introduce the notion of an adversary, which perturbs observed historical time series to increase a robot's ultimate control cost. Specifically, we model this interaction as a zero-sum two-player game between a robot's forecaster and this hypothetical adversary. We show that our proposed game may be solved to a local Nash equilibrium using gradient-based optimization techniques. Furthermore, we show that a forecaster trained with our method performs 30.14% better on out-of-distribution real-world lane change data than baselines.
引用
收藏
页码:5566 / 5573
页数:8
相关论文
共 41 条
  • [1] Agarwal N., 2019, INT C MACH LEARN, V97, P111
  • [2] Agarwal S., 2022, 6 ANN C ROB LEARN
  • [3] Agrawal A., 2019, Advances in Neural Information Processing Systems
  • [4] Social LSTM: Human Trajectory Prediction in Crowded Spaces
    Alahi, Alexandre
    Goel, Kratarth
    Ramanathan, Vignesh
    Robicquet, Alexandre
    Li Fei-Fei
    Savarese, Silvio
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 961 - 971
  • [5] Arjovsky M., 2017, ICLR
  • [6] Bartoli F., 2017, ARXIV170502503
  • [7] Bas<comma>ar T., 1998, DYNAMIC NONCOOPERATI, DOI DOI 10.1137/1.978161
  • [8] Conover W., 1999, WILEY SERIES PROBABI, VVIII, P584
  • [9] Esfahani P.M., 2015, Data-driven distributionally robust optimization using the Wasserstein metric: Performance guarantees and tractable reformulations
  • [10] Soft plus Hardwired attention: An LSTM framework for human trajectory prediction and abnormal event detection
    Fernando, Tharindu
    Denman, Simon
    Sridharan, Sridha
    Fookes, Clinton
    [J]. NEURAL NETWORKS, 2018, 108 : 466 - 478