Bayesian Intent Prediction for Fast Maneuvering Objects using Variable Rate Particle Filters

The motion of a tracked object often has long term underlying dependencies due to premeditated actions dictated by intent, such as destination. Revealing this intent, as early as possible, can enable advanced intelligent system functionalities for conflict/opportunity detection and automated decision making, for instance in surveillance and human computer interaction. This paper presents a novel Bayesian intent inference framework that utilises sequential Monte Carlo (SMC) methods to determine the destination of a tracked object exhibiting unknown jump behaviour. The latter can arise from the object undertaking fast maneuvers (e.g. for obstacle avoidance) and/or due to external uncontrollable environmental perturbations. Suitable intent-driven stochastic models and inference routines are introduced. The effectiveness of the proposed approach is demonstrated using synthetic and real data.

[1]  Paolo Braca,et al.  Prediction of Rendezvous in Maritime Situational Awareness , 2018, 2018 21st International Conference on Information Fusion (FUSION).

[2]  James K. Murphy,et al.  Bayesian Intent Prediction in Object Tracking Using Bridging Distributions. , 2016, IEEE transactions on cybernetics.

[3]  Andrew Golightly.  Bayesian Filtering for Jump-Diffusions With Application to Stochastic Volatility , 2009 .

[4]  Langford B. White,et al.  Destination-aware target tracking via syntactic signal processing , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Simon J. Godsill,et al.  Forecasting High-Frequency Futures Returns Using Online Langevin Dynamics , 2012, IEEE Journal of Selected Topics in Signal Processing.

[6]  Lee Skrypchuk,et al.  Intent Inference for Hand Pointing Gesture-Based Interactions in Vehicles , 2016, IEEE Transactions on Cybernetics.

[7]  Simon J. Godsill,et al.  Particle Smoothing Algorithms for Variable Rate Models , 2013, IEEE Transactions on Signal Processing.

[8]  Simon J. Godsill,et al.  Models and Algorithms for Tracking of Maneuvering Objects Using Variable Rate Particle Filters , 2007, Proceedings of the IEEE.

[9]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[10]  Roland Siegwart,et al.  Inferring Pedestrian Motions at Urban Crosswalks , 2019, IEEE Transactions on Intelligent Transportation Systems.

[11]  M. Pitt,et al.  Filtering via Simulation: Auxiliary Particle Filters , 1999 .

[12]  Simon J. Godsill,et al.  Filtering perturbed in-vehicle pointing gesture trajectories: Improving the reliability of intent inference , 2014, 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP).

[13]  Simo Särkkä,et al.  Recursive Bayesian inference on stochastic differential equations , 2006 .

[14]  Vikram Krishnamurthy,et al.  Syntactic Enhancement to VSIMM for Roadmap Based Anomalous Trajectory Detection: A Natural Language Processing Approach , 2016, IEEE Transactions on Signal Processing.

[15]  Tadahiro Taniguchi,et al.  Unsupervised drive topic finding from driving behavioral data , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[16]  Paolo Braca,et al.  Data Driven Vessel Trajectory Forecasting Using Stochastic Generative Models , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Simon J. Godsill,et al.  Particle Filtering: the First 25 Years and beyond , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Martial Hebert,et al.  Activity Forecasting , 2012, ECCV.

[19]  Lydia Tapia,et al.  Stochastic Ensemble Simulation motion planning in stochastic dynamic environments , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Brian D. Ziebart,et al.  Discriminatively Learning Inverse Optimal Control Models for Predicting Human Intentions , 2019, AAMAS.

[21]  Simon J. Godsill,et al.  A Meta-Tracking Approach for Predicting the Driver or Passenger Intent , 2018, 2018 21st International Conference on Information Fusion (FUSION).

[22]  Bashar I. Ahmad,et al.  Intelligent Interactive Displays in Vehicles with Intent Prediction: A Bayesian framework , 2017, IEEE Signal Processing Magazine.

[23]  Christophe Andrieu,et al.  PARTICLE FILTERS FOR CONTINUOUS-TIME JUMP MODELS IN TRACKING APPLICATIONS , 2007 .

[24]  Paolo Braca,et al.  Modeling vessel kinematics using a stochastic mean-reverting process for long-term prediction , 2016, IEEE Transactions on Aerospace and Electronic Systems.

[25]  Vikram Krishnamurthy,et al.  Spatiotemporal trajectory models for metalevel target tracking , 2015, IEEE Aerospace and Electronic Systems Magazine.

[26]  Robert Fitch,et al.  Bayesian intention inference for trajectory prediction with an unknown goal destination , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[27]  Vikram Krishnamurthy,et al.  Meta-level tracking for gestural intent recognition , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).