Interactive Trajectory Planning with Learning-based Distributionally Robust Model Predictive Control and Markov Systems
Not on the map. Why?
Abstract (arXiv)
We investigate interactive trajectory planning subject to uncertainty in the decisions of surrounding agents. To control the ego-agent, we aim to first learn the decision distribution and solve a Stochastic Model Predictive Control (SMPC) problem. To account for errors in the learned distribution, we show that it is possible to utilize Probably Approximately Correct (PAC) learning in combination with Distributionally Robust (DR) optimization to obtain a solution which accounts for the errors induced by the learning model. The results indicate that our PAC learning-based DR-MPC framework provides a method to interpolate between a robust MPC and an omnipotent SMPC, based on the available number of samples.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 21 references that are in the map. First posted on arXiv 8 May 2026.
Builds on
8 of 21 references.
References · 8
- 2022Safe Planning in Dynamic Environments using Conformal Predictioncited by 112
- 2021Interactive multi-modal motion planning with Branch Model Predictive Controlcited by 21
- 2021Stochastic MPC with Multi-modal Predictions for Traffic Intersectionscited by 5
- 2021A General Framework for Learning-Based Distributionally Robust MPC of Markov Jump Systemscited by 4
- 2019Risk-averse risk-constrained optimal controlcited by 2
- 2023Interaction-Aware Trajectory Prediction and Planning in Dense Highway Traffic using Distributed Model Predictive Controlcited by 1
- 2025Combined Stochastic and Robust Optimization for Electric Autonomous Mobility-on-Demand with Nested Benders Decompositioncited by 1
- 2025Tight Collision Avoidance for Stochastic Optimal Control: with Applications in Learning-based, Interactive Motion Planningcited by 1
Built on by
Not cited yet.