TR2018-164

Motion Planning of Autonomous Road Vehicles by Particle Filtering


    •  Berntorp, K., Hoang, T., Di Cairano, S., "Motion Planning of Autonomous Road Vehicles by Particle Filtering", IEEE Transactions on Intelligent Vehicles, DOI: 10.1109/​TIV.2019.2904394, Vol. 4, No. 2, pp. 197-210, December 2018.
      BibTeX TR2018-164 PDF
      • @article{Berntorp2018dec,
      • author = {Berntorp, Karl and Hoang, Tru and Di Cairano, Stefano},
      • title = {Motion Planning of Autonomous Road Vehicles by Particle Filtering},
      • journal = {IEEE Transactions on Intelligent Vehicles},
      • year = 2018,
      • volume = 4,
      • number = 2,
      • pages = {197--210},
      • month = dec,
      • doi = {10.1109/TIV.2019.2904394},
      • url = {https://www.merl.com/publications/TR2018-164}
      • }
  • MERL Contacts:
  • Research Areas:

    Control, Dynamical Systems

Abstract:

This paper describes a probabilistic method for real-time decision making and motion planning for autonomous vehicles. Our approach relies on that driving on road networks implies a priori defined requirements that the motion planner should satisfy. Starting from an initial state of the vehicle, a map, the obstacles in the region of interest, and a goal region, we formulate the motion-planning problem as a nonlinear nonGaussian estimation problem, which we solve using particle filtering. We assign probabilities to the generated trajectories according to their likelihood of obeying the driving requirements. Decision making and collision avoidance is naturally integrated in the approach. We develop a receding-horizon implementation and verify the method in simulated real road scenarios and in an experimental validation using a scaled mobile robot setup with car-like dynamics. The results show that the method generates dynamically feasible trajectories for a number of scenarios, such as collision avoidance, overtaking, and traffic-jam scenarios. In addition, the computation times and memory requirements indicate that the method is suitable for real-time implementation.

 

  • Related News & Events

    •  NEWS    MERL researcher Stefano Di Cairano taught short course for European Embedded Control Institute
      Date: June 10, 2019 - June 14, 2019
      Where: Paris
      MERL Contact: Stefano Di Cairano
      Research Areas: Control, Dynamical Systems, Optimization
      Brief
      • MERL researcher Stefano Di Cairano and Prof. Ilya Kolmanovsky, Dept. Aerospace Engineering, the University of Michigan, were invited to teach a class on "Predictive and Optimization Based Control for Automotive and Aerospace Application" at the 2019 International Graduate School in Control, of the European Embedded Control Institute (EECI). Every year EECI invites world renown experts to teach 21-hours class modules, mostly for PhD students but also for professionals, on selected control subjects. Stefano and Ilya's class was attended by 30 "students" from both academia and industry, from all around the world, interested in automotive and aerospace control. The module described the fundamentals of modeling and control design in automotive and aerospace through lectures, real world examples and exercises, and placed particular emphasis on techniques such as MPC, reference governors, and optimal control.
    •  
    •  NEWS    IEEE Control Systems Magazine interviews Stefano Di Cairano
      Date: April 15, 2019
      MERL Contact: Stefano Di Cairano
      Research Area: Control
      Brief
      • Stefano Di Cairano, senior team leader and distinguished research scientist in the Control and Dynamical Systems group, was interviewed in the April 2019 issue of IEEE Control Systems Magazine. Stefano described himself, promising opportunities in the control field, and how his passion for control research fits well into the industrial research laboratory setting at MERL. It is very good reading for any young researcher considering possible career trajectories.
    •  
    •  NEWS    Stefano Di Cairano to give invited address at 3rd IAVSD Workshop on Dynamics of Road Vehicles: Connected and Automated Vehicles
      Date: April 28, 2019
      Where: 3rd IAVSD Workshop on Dynamics of Road Vehicles: Connected and Automated Vehicles
      MERL Contact: Stefano Di Cairano
      Research Areas: Control, Optimization, Robotics
      Brief
      • Stefano Di Cairano, Distinguished Scientist and Senior Team Leader in the Control and Dynamical Systems Group, will give an invited talk entitled: "Modularity, integration and synergy in architectures for autonomous driving" that covers recent work in the lab concerning building a modular, robust control framework for autonomous driving.
    •  
  • Related Publication

  •  Berntorp, K., Inani, P., Quirynen, R., Di Cairano, S., "Motion Planning of Autonomous Road Vehicles by Particle Filtering: Implementation and Validation", American Control Conference (ACC), DOI: 10.23919/​ACC.2019.8815309, July 2019, pp. 1382-1387.
    BibTeX TR2019-062 PDF
    • @inproceedings{Berntorp2019jul2,
    • author = {Berntorp, Karl and Inani, Pranav and Quirynen, Rien and Di Cairano, Stefano},
    • title = {Motion Planning of Autonomous Road Vehicles by Particle Filtering: Implementation and Validation},
    • booktitle = {American Control Conference (ACC)},
    • year = 2019,
    • pages = {1382--1387},
    • month = jul,
    • publisher = {IEEE},
    • doi = {10.23919/ACC.2019.8815309},
    • url = {https://www.merl.com/publications/TR2019-062}
    • }