Navigating Congested Environments with Risk Level Sets

In this paper, we address the problem of navigating in a cluttered environment by introducing a congestion cost that maps the density and motion of objects to an occupancy risk. We propose that an agent can choose a “risk level set” from this cost function and construct a planning space from this set. In choosing different levels of risk, the agent adjusts its interactions with the other agents. From the assumption that agents are self-preserving, we show that any agent planning within their risk level set will avoid collisions with other agents. We then present an application of planning with risk level sets in the framework of an autonomous vehicle driving along a highway. Using the risk level sets, the agent can determine safe zones when planning a sequence of lane changes. Through simulations in Matlab, we demonstrate how the choice of risk threshold manifests as aggressive or conservative behavior.

[1]  Oliver Brock,et al.  High-speed navigation using the global dynamic window approach , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[2]  José Eugenio Naranjo,et al.  Lane-Change Fuzzy Control in Autonomous Vehicles for the Overtaking Maneuver , 2008, IEEE Transactions on Intelligent Transportation Systems.

[3]  Wilko Schwarting,et al.  Recursive conflict resolution for cooperative motion planning in dynamic highway traffic , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[4]  Amnon Shashua,et al.  Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving , 2016, ArXiv.

[5]  Elias B. Kosmatopoulos,et al.  Collision avoidance analysis for lane changing and merging , 1999, IEEE Trans. Veh. Technol..

[6]  Zhaodan Kong,et al.  A Survey of Motion Planning Algorithms from the Perspective of Autonomous UAV Guidance , 2010, J. Intell. Robotic Syst..

[7]  Paulo Tabuada,et al.  Control barrier function based quadratic programs with application to adaptive cruise control , 2014, 53rd IEEE Conference on Decision and Control.

[8]  Francesco Borrelli,et al.  Scenario model predictive control for lane change assistance on highways , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[9]  Li Wang,et al.  Control Barrier Certificates for Safe Swarm Behavior , 2015, ADHS.

[10]  Petros G. Voulgaris,et al.  Distributed Coordination Control for Multi-Robot Networks Using Lyapunov-Like Barrier Functions , 2016, IEEE Transactions on Automatic Control.

[11]  Martin Buss,et al.  Interactive scene prediction for automotive applications , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[12]  Michael Schreckenberg,et al.  Particle hopping models for two-lane traffic with two kinds of vehicles: Effects of lane-changing rules , 1997 .

[13]  Petter Ögren,et al.  A convergent dynamic window approach to obstacle avoidance , 2005, IEEE Transactions on Robotics.

[14]  Christian Schlegel.  Fast local obstacle avoidance under kinematic and dynamic constraints for a mobile robot , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[15]  Kai Nagel,et al.  Realistic multi-lane traffic rules for cellular automata , 1997 .

[16]  Calin Belta,et al.  Discrete abstractions for robot motion planning and control in polygonal environments , 2005, IEEE Transactions on Robotics.

[17]  Moshe Ben-Akiva,et al.  MODELS OF FREEWAY LANE CHANGING AND GAP ACCEPTANCE BEHAVIOR , 1996 .

[18]  Shekhar Verma,et al.  Neural Network Based Lane Change Trajectory Prediction in Autonomous Vehicles , 2011, Trans. Comput. Sci..

[19]  Peter Hidas,et al.  MODELLING LANE CHANGING AND MERGING IN MICROSCOPIC TRAFFIC SIMULATION , 2002 .