Simulating Crowds and Autonomous Vehicles

Understanding how people view and interact with autonomous vehicles is important to guide future directions of research. One such way of aiding understanding is through simulations of virtual environments involving people and autonomous vehicles. We present a simulation model that incorporates people and autonomous vehicles in a shared urban space. The model is able to simulate many thousands of people and vehicles in real-time. This is achieved by use of GPU hardware, and through a novel linear program solver optimized for large numbers of problems on the GPU. The model is up to 30 times faster than the equivalent multi-core CPU model.

[1]  Paul Richmond,et al.  Two-dimensional batch linear programming on the GPU , 2019, J. Parallel Distributed Comput..

[2]  Iyad Rahwan,et al.  The social dilemma of autonomous vehicles , 2015, Science.

[3]  B. Schönfisch,et al.  Synchronous and asynchronous updating in cellular automata. , 1999, Bio Systems.

[4]  Dinesh Manocha,et al.  Reciprocal collision avoidance with acceleration-velocity obstacles , 2011, 2011 IEEE International Conference on Robotics and Automation.

[5]  Jan Gogoll,et al.  Autonomous Cars: In Favor of a Mandatory Ethics Setting , 2016, Science and Engineering Ethics.

[6]  Wenwen Zhang,et al.  Exploring the impact of shared autonomous vehicles on urban parking demand: An agent-based simulation approach , 2015 .

[7]  Ebru Akcapinar Sezer,et al.  Combining GPU-generated linear trajectory segments to create collision-free paths for real-time ambient crowds , 2018, Graph. Model..

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

[9]  Shiyu Zhao,et al.  Velocity Obstacle Approaches for Multi-Agent Collision Avoidance , 2019, Unmanned Syst..

[10]  Francesco Ciari,et al.  Agent-based simulation of autonomous cars , 2015, 2015 American Control Conference (ACC).

[11]  John D. Owens,et al.  Gunrock: a high-performance graph processing library on the GPU , 2015, PPoPP.

[12]  Victor J. Blue,et al.  Cellular Automata Microsimulation of Bidirectional Pedestrian Flows , 1999 .

[13]  Ming C. Lin,et al.  Motion planning and autonomy for virtual humans , 2008, SIGGRAPH '08.

[14]  Zhengguo Li,et al.  Generalized Reciprocal Collision Avoidance for Non-holonomic Robots , 2019, 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[15]  Patrick Lin.  Why Ethics Matters for Autonomous Cars , 2016 .

[16]  Matthias Althoff,et al.  Comparison of Markov Chain Abstraction and Monte Carlo Simulation for the Safety Assessment of Autonomous Cars , 2011, IEEE Transactions on Intelligent Transportation Systems.

[17]  Mohak Shah,et al.  Is it Safe to Drive? An Overview of Factors, Challenges, and Datasets for Driveability Assessment in Autonomous Driving , 2018, ArXiv.

[18]  N. McBride.  The ethics of driverless cars , 2016, SIGCAS Comput. Soc..

[19]  Sebastian Hörl,et al.  Agent-based simulation of autonomous taxi services with dynamic demand responses , 2017, ANT/SEIT.

[20]  Christian Laugier,et al.  Dynamic Obstacle Avoidance in uncertain environment combining PVOs and Occupancy Grid , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[21]  I. C. MariAnne Karlsson,et al.  Setting the stage for autonomous cars: a pilot study of future autonomous driving experiences , 2015 .

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

[23]  John Dingliana,et al.  Holonomic collision avoidance for virtual crowds , 2015, SCA '14.

[24]  Malte Risto,et al.  The social behavior of autonomous vehicles , 2016, UbiComp Adjunct.

[25]  Avi Bleiweiss,et al.  Multi Agent Navigation on the GPU , 2011 .

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

[27]  Dinesh Manocha,et al.  Real-time reciprocal collision avoidance with elliptical agents , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

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

[29]  Daniela M. Romano,et al.  Agent-based Large Scale Simulation of Pedestrians With Adaptive Realistic Navigation Vector Fields , 2010, TPCG.

[30]  J L Adler,et al.  Emergent Fundamental Pedestrian Flows from Cellular Automata Microsimulation , 1998 .

[31]  Dinesh Manocha,et al.  Proxemic group behaviors using reciprocal multi-agent navigation , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[32]  D. Romano,et al.  A HIGH PERFORMANCE FRAMEWORK FOR AGENT BASED PEDESTRIAN DYNAMICS ON GPU HARDWARE , 2008 .

[33]  Daniel Thalmann,et al.  Populating virtual environments with crowds , 2006, VRCIA '06.

[34]  Erwin Prassler,et al.  Recursive Probabilistic Velocity Obstacles for Reflective Navigation , 2003, FSR.

[35]  Fanghong Guo,et al.  Reciprocal Collision Avoidance for Nonholonomic Mobile Robots , 2018, 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV).

[36]  Nuria Pelechano,et al.  Introduction to Crowd Simulation , 2017, Eurographics.

[37]  Dinesh Manocha,et al.  ClearPath: highly parallel collision avoidance for multi-agent simulation , 2009, SCA '09.

[38]  Dinesh Manocha,et al.  Dynamic group behaviors for interactive crowd simulation , 2016, Symposium on Computer Animation.

[39]  Raimund Seidel,et al.  Small-dimensional linear programming and convex hulls made easy , 1991, Discret. Comput. Geom..

[40]  John K. Tsotsos,et al.  Autonomous Vehicles That Interact With Pedestrians: A Survey of Theory and Practice , 2018, IEEE Transactions on Intelligent Transportation Systems.

[41]  Yasuaki Abe,et al.  Collision avoidance method for multiple autonomous mobile agents by implicit cooperation , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[42]  Paul Richmond,et al.  Fast Simulation of Crowd Collision Avoidance , 2019, CGI.

[43]  Ming C. Lin,et al.  Aggregate dynamics for dense crowd simulation , 2009, ACM Trans. Graph..