Anticipatory Navigation in Crowds by Probabilistic Prediction of Pedestrian Future Movements

Critical for the coexistence of humans and robots in dynamic environments is the capability for agents to understand each other’s actions, and anticipate their movements. This paper presents Stochastic Process Anticipatory Navigation (SPAN), a framework that enables nonholonomic robots to navigate in environments with crowds, while anticipating and accounting for the motion patterns of pedestrians. To this end, we learn a predictive model to predict continuous-time stochastic processes to model future movement of pedestrians. Anticipated pedestrian positions are used to conduct chance constrained collision-checking, and are incorporated into a time-to-collision control problem. An occupancy map is also integrated to allow for probabilistic collision-checking with static obstacles. We demonstrate the capability of SPAN in crowded simulation environments, as well as with a real-world pedestrian dataset.

[1]  John C Hayward,et al.  NEAR-MISS DETERMINATION THROUGH USE OF A SCALE OF DANGER , 1972 .

[2]  Oussama Khatib,et al.  Real-Time Obstacle Avoidance for Manipulators and Mobile Robots , 1985, Autonomous Robot Vehicles.

[3]  Charles E. Thorpe,et al.  Integrated mobile robot control , 1991 .

[4]  M. Powell.  A Direct Search Optimization Method That Models the Objective and Constraint Functions by Linear Interpolation , 1994 .

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

[6]  S. LaValle.  Rapidly-exploring random trees : a new tool for path planning , 1998 .

[7]  P. Dutilleul.  The mle algorithm for the matrix normal distribution , 1999 .

[8]  Andrew Howard,et al.  Design and use paradigms for Gazebo, an open-source multi-robot simulator , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[9]  Jonathan P. How,et al.  Motion Planning in Complex Environments using Closed-loop Prediction , 2008 .

[10]  Siddhartha S. Srinivasa,et al.  CHOMP: Gradient optimization techniques for efficient motion planning , 2009, 2009 IEEE International Conference on Robotics and Automation.

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

[12]  T. Higuchi.  Visuomotor Control of Human Adaptive Locomotion: Understanding the Anticipatory Nature , 2013, Front. Psychol..

[13]  Ioannis Karamouzas,et al.  Universal power law governing pedestrian interactions. , 2014, Physical review letters.

[14]  Jur P. van den Berg,et al.  Generalized reciprocal collision avoidance , 2015, Int. J. Robotics Res..

[15]  Fabio Tozeto Ramos,et al.  Hilbert maps: Scalable continuous occupancy mapping with stochastic gradient descent , 2015, Robotics: Science and Systems.

[16]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[17]  James M. Rehg,et al.  Aggressive driving with model predictive path integral control , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[18]  Roland Siegwart,et al.  Fast nonlinear Model Predictive Control for unified trajectory optimization and tracking , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Silvio Savarese,et al.  Social LSTM: Human Trajectory Prediction in Crowded Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Rahul Narain,et al.  Implicit crowds , 2017, ACM Trans. Graph..

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

[22]  Byron Boots,et al.  RMPflow: A Computational Graph for Automatic Motion Policy Generation , 2018, WAFR.

[23]  Silvio Savarese,et al.  Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[25]  Lionel Ott,et al.  Kernel Trajectory Maps for Multi-Modal Probabilistic Motion Prediction , 2019, CoRL.

[26]  Javier Alonso-Mora,et al.  Chance-Constrained Collision Avoidance for MAVs in Dynamic Environments , 2019, IEEE Robotics and Automation Letters.

[27]  Lionel Ott,et al.  Spatiotemporal Learning of Directional Uncertainty in Urban Environments With Kernel Recurrent Mixture Density Networks , 2019, IEEE Robotics and Automation Letters.

[28]  Fabio Tozeto Ramos,et al.  Balancing Global Exploration and Local-connectivity Exploitation with Rapidly-exploring Random disjointed-Trees , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[29]  Stephen J. Guy,et al.  NH-TTC: A gradient-based framework for generalized anticipatory collision avoidance , 2019, Robotics: Science and Systems.

[30]  Dariu M. Gavrila,et al.  Human motion trajectory prediction: a survey , 2019, Int. J. Robotics Res..

[31]  THÖR: Human-Robot Navigation Data Collection and Accurate Motion Trajectories Dataset , 2019, IEEE Robotics and Automation Letters.