Interaction-Aware Model Predictive Path Integral Control for Motion Planning in Urban Settings

Elia Trevisan1 Alejandro Gonzalez-Garcia2 Jan Swevers2 Javier Alonso-Mora1

1TU Delft 2KU Leuven

arXiv (coming soon) PyTorch Code Related Publications

Onboard IA-MPPI in the Real-World

The videos below show head-on and crossing scenarios onboard two quarterscale Roboat vessels. Localization and planning is computed onboard, with IA-MPPI performing simultaneous prediction and planning at 10Hz with 100 steps ahead horizons (10 seconds). The conflicts are resolves according to navigation rules, i.e. passing head-on on the right-side, and giving right-of-way to the right.

Abstract

Autonomous vehicles that operate in urban environments shall comply with existing rules and reason about the interactions with other decision-making agents. In this paper, we introduce a decentralized and communication-free interaction-aware motion planner and apply it to Autonomous Surface Vessels (ASVs) in urban canals. We build upon a sampling-based method, namely Model Predictive Path Integral control (MPPI), and employ it to, in each time instance, compute both a collision-free trajectory for the vehicle and a prediction of other agents' trajectories, thus modeling interactions. To improve the method's efficiency in multi-agent scenarios, we introduce a two-stage sample evaluation strategy and define an appropriate cost function to achieve rule compliance. We evaluate this decentralized approach in simulations with multiple vessels in real scenarios extracted from Amsterdam's canals, showing superior performance than a state-of-the-art trajectory optimization framework and robustness when encountering different types of agents.

Dynamic Risk-Aware MPPI for Mobile Robots in Crowds via Efficient Monte Carlo Approximations
Elia Trevisan, Khaled A. Mustafa, Godert Notten, Xinwei Wang, Javier Alonso-Mora. In IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2025.

web pdf

Active Disturbance Rejection Control (ADRC) for Trajectory Tracking of a Seagoing USV: Design, Simulation, and Field Experiments
Jelmer van der Saag, Elia Trevisan, Wouter Falkena, Javier Alonso-Mora. In IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2025.

web pdf

Sampling-based Model Predictive Control Leveraging Parallelizable Physics Simulations
Corrado Pezzato, Chadi Salmi, Elia Trevisan, Max Spahn, Javier Alonso-Mora, Carlos Hernández Corbato. In IEEE Robotics and Automation Letters (RA-L), 2025.

web

Multi-Modal MPPI and Active Inference for Reactive Task and Motion Planning
Yuezhe Zhang, Corrado Pezzato, Elia Trevisan, Chadi Salmi, Carlos Hernández Corbato, Javier Alonso-Mora. In IEEE Robotics and Automation Letters (RA-L), 2024.

pdf web

Biased-MPPI: Informing Sampling-Based Model Predictive Control by Fusing Ancillary Controllers
Elia Trevisan, Javier Alonso-Mora. In IEEE Robotics and Automation Letters (RA-L), 2024.

pdf web

Interaction-Aware Sampling-Based MPC with Learned Local Goal Predictions
W. Jansma, E. Trevisan, A. Serra-Gomez, J. Alonso-Mora. In Proc. IEEE International Symposium on Multi-Robot and Multi-Agent Systems, 2023.

pdf web

Sampling-Based MPC Using a GPU-parallelizable Physics Simulator as Dynamic Model: an Open Source Implementation with IsaacGym
C. Pezzato, C. Salmi, E. Trevisan, J. Alonso-Mora, C. Hernandez Corbato. In Embracing Contacts Workshop at IEEE Int. Conf. on Robotics and Automation (ICRA), 2023.

pdf code publisher

Multi-Agent Path Integral Control for Interaction-Aware Motion Planning in Urban Canals
L. Streichenberg, E. Trevisan, J. J. Chung, R. Siegwart, J. Alonso-Mora. In IEEE Int. Conf. on Robotics and Automation (ICRA), 2023.

pdf publisher

Regulations Aware Motion Planning for Autonomous Surface Vessels in Urban Canals
J. de Vries, E. Trevisan, J. van der Toorn, T. Das, B. Brito, J. Alonso-Mora. In Proc. IEEE Int. Conf. on Robotics and Automation (ICRA), 2022.

publisher pdf video

Back to Publications