SUMMIT: A Simulator for Urban Driving in Massive Mixed Traffic

Autonomous driving in an unregulated urban crowd is an outstanding challenge, especially, in the presence of many aggressive, high-speed traffic participants. This paper presents SUMMIT, a high-fidelity simulator that facilitates the development and testing of crowd-driving algorithms. By leveraging the open-source OpenStreetMap map database and a heterogeneous multi-agent motion prediction model developed in our earlier work, SUMMIT simulates dense, unregulated urban traffic for heterogeneous agents at any worldwide locations that OpenStreetMap supports. SUMMIT is built as an extension of CARLA and inherits from it the physics and visual realism for autonomous driving simulation. SUMMIT supports a wide range of applications, including perception, vehicle control and planning, and end-to-end learning. We provide a context-aware planner together with benchmark scenarios and show that SUMMIT generates complex, realistic traffic behaviors in challenging crowd-driving settings.

[1]  Christos Dimitrakakis,et al.  TORCS, The Open Racing Car Simulator , 2005 .

[2]  Vladlen Koltun,et al.  Playing for Benchmarks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  David Hsu,et al.  HyP-DESPOT: A hybrid parallel algorithm for online planning under uncertainty , 2018, Robotics: Science and Systems.

[4]  Dinesh Manocha,et al.  Efficient and Safe Vehicle Navigation Based on Driver Behavior Classification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[5]  Martin Lauer,et al.  CoInCar-Sim: An Open-Source Simulation Framework for Cooperatively Interacting Automobiles , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[6]  Dinesh Manocha,et al.  The Hybrid Reciprocal Velocity Obstacle , 2011, IEEE Transactions on Robotics.

[7]  Paolo Fiorini,et al.  Motion Planning in Dynamic Environments Using Velocity Obstacles , 1998, Int. J. Robotics Res..

[8]  Gonzalo Ferrer,et al.  Robot companion: A social-force based approach with human awareness-navigation in crowded environments , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Bernard Ghanem,et al.  Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications , 2017, International Journal of Computer Vision.

[10]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[11]  Paul Newman,et al.  1 year, 1000 km: The Oxford RobotCar dataset , 2017, Int. J. Robotics Res..

[12]  Ken Goldberg,et al.  FLUIDS: A First-Order Local Urban Intersection Driving Simulator , 2018 .

[13]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[14]  Daniela Rus,et al.  Context and Intention Aware Planning for Urban Driving , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[15]  Paul A. Beardsley,et al.  Optimal Reciprocal Collision Avoidance for Multiple Non-Holonomic Robots , 2010, DARS.

[16]  Simon Oh,et al.  SimMobility Short-Term: An Integrated Microscopic Mobility Simulator , 2017 .

[17]  David Hsu,et al.  LeTS-Drive: Driving in a Crowd by Learning from Tree Search , 2019, Robotics: Science and Systems.

[18]  Dinesh Manocha,et al.  AutonoVi-Sim: Autonomous Vehicle Simulation Platform with Weather, Sensing, and Traffic Control , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[20]  Dinesh Manocha,et al.  Generalized velocity obstacles , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[21]  Germán Ros,et al.  CARLA: An Open Urban Driving Simulator , 2017, CoRL.

[22]  P. Molnár.  Social Force Model for Pedestrian Dynamics Typeset Using Revt E X 1 , 1995 .

[23]  Xiaogang Jin,et al.  Force-based Heterogeneous Traffic Simulation for Autonomous Vehicle Testing , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[24]  Yun-Pang Flötteröd,et al.  Microscopic Traffic Simulation using SUMO , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[25]  Rainald Löhner,et al.  On the modeling of pedestrian motion , 2010 .

[26]  Jakub W. Pachocki,et al.  Learning dexterous in-hand manipulation , 2018, Int. J. Robotics Res..

[27]  Dinesh Manocha,et al.  PORCA: Modeling and Planning for Autonomous Driving Among Many Pedestrians , 2018, IEEE Robotics and Automation Letters.

[28]  Dinesh Manocha,et al.  Reciprocal n-Body Collision Avoidance , 2011, ISRR.

[29]  R. C. Coulter,et al.  Implementation of the Pure Pursuit Path Tracking Algorithm , 1992 .

[30]  Dinesh Manocha,et al.  Reciprocal Velocity Obstacles for real-time multi-agent navigation , 2008, 2008 IEEE International Conference on Robotics and Automation.

[31]  Yuanfu Luo,et al.  GAMMA: A General Agent Motion Prediction Model for Autonomous Driving , 2019, ArXiv.

[32]  Luc Van Gool,et al.  You'll never walk alone: Modeling social behavior for multi-target tracking , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[33]  Paul A. Beardsley,et al.  Reciprocal collision avoidance for multiple car-like robots , 2012, 2012 IEEE International Conference on Robotics and Automation.