Robust Forecasting for Robotic Control: A Game-Theoretic Approach
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 22 Sep 2022.
Builds on
29 of 45 references.
References · 29
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2022Generative Adversarial Networkscited by 5,603
- 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
- 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
- 2019Differentiable Convex Optimization Layerscited by 458
- 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
- 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
- 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 285
- 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
17 more
- 2020Transformer Networks for Trajectory Forecastingcited by 180
- 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 178
- 2019Online Control with Adversarial Disturbancescited by 92
- 2021Learning to Predict Vehicle Trajectories with Model-based Planningcited by 63
- 2017Multimodal Probabilistic Model-Based Planning for Human-Robot Interactioncited by 50
- 2018On Gradient-Based Learning in Continuous Gamescited by 46
- 2017Soft + Hardwired Attention: An LSTM Framework for Human Trajectory Prediction and Abnormal Event Detectioncited by 42
- 2019On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Gamescited by 35
- 2017Context-Aware Trajectory Predictioncited by 31
- 2019Convergence of Learning Dynamics in Stackelberg Gamescited by 28
- 2014On the Characterization of Local Nash Equilibria in Continuous Gamescited by 21
- 2021Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithmscited by 18
- 2021The Computation of Approximate Generalized Feedback Nash Equilibriacited by 7
- 2019Game Theoretic Optimization via Gradient-based Nikaido-Isoda Functioncited by 6
- 2020Generating Adversarial Disturbances for Controller Verificationcited by 4
- 2022Synthesizing Adversarial Visual Scenarios for Model-Based Robotic Controlcited by 4
- 2022Adversarial Examples for Model-Based Control: A Sensitivity Analysiscited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.