Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/springer-journals/multipolicy-decision-making-for-autonomous-driving-via-changepoint-LMjfm5Wsy4
References (54)
-
C. Urmson, Joshua Anhalt, J. Bagnell, Christopher Baker, R. Bittner, M. Clark, J. Dolan, D. Duggins, Tugrul Galatali, Christopher Geyer, Michele Gittleman, Sam Harbaugh, M. Hebert, T. Howard, Sascha Kolski, A. Kelly, M. Likhachev, M. McNaughton, Nick Miller, K. Peterson, Brian Pilnick, R. Rajkumar, P. Rybski, B. Salesky, Young-Woo Seo, Sanjiv Singh, Jarrod Snider, A. Stentz, W. Whittaker, Ziv Wolkowicki, Jason Ziglar, Hong Bae, Thomas Brown, Daniel Demitrish, B. Litkouhi, J. Nickolaou, Varsha Sadekar, Wende Zhang, Joshua Struble, Michael Taylor, M. Darms, D. Ferguson (2008)
Autonomous driving in urban environments: Boss and the Urban ChallengeJournal of Field Robotics, 25
-
S. Chung, Han-Pang Huang (2011)
Robot Motion Planning in Dynamic Uncertain EnvironmentsAdvanced Robotics, 25
-
(2011)
Gaussian process regression flow for analysis ofmotion trajectories -
Frank Havlak, M. Campbell (2010)
Discrete and Continuous, Probabilistic Anticipation for Autonomous Robots in Urban EnvironmentsIEEE Transactions on Robotics, 30
-
R. Kowalczyk, J. Müller, H. Tianfield, R. Unland (2002)
Agent Technologies, Infrastructures, Tools, and Applications for E-Services, 2592
-
E. Galceran, Edwin Olson, R. Eustice (2015)
Augmented vehicle tracking under occlusions for decision-making in autonomous driving2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
-
Simon Ulbrich, M. Maurer (2013)
Probabilistic online POMDP decision making for lane changes in fully automated driving16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013)
-
M. Werling, Julius Ziegler, S. Kammel, S. Thrun (2010)
Optimal trajectory generation for dynamic street scenarios in a Frenét Frame2010 IEEE International Conference on Robotics and Automation
-
Takeshi Ohki, K. Nagatani, Kazuya Yoshida (2010)
Collision avoidance method for mobile robot considering motion and personal spaces of evacuees2010 IEEE/RSJ International Conference on Intelligent Robots and Systems
-
M. Kuderer, S. Gulati, Wolfram Burgard (2015)
Learning driving styles for autonomous vehicles from demonstration2015 IEEE International Conference on Robotics and Automation (ICRA)
-
J. Joseph, F. Doshi-Velez, Albert Huang, N. Roy (2011)
A Bayesian nonparametric approach to modeling motion patternsAutonomous Robots, 31
-
Haoyu Bai, David Hsu, Wee Lee (2013)
Integrated perception and planning in the continuous space: A POMDP approachThe International Journal of Robotics Research, 33
-
V. Chandola, A. Banerjee, Vipin Kumar (2009)
Anomaly detection: A surveyACM Comput. Surv., 41
-
A. Broadhurst, S. Baker, T. Kanade (2005)
Monte Carlo road safety reasoningIEEE Proceedings. Intelligent Vehicles Symposium, 2005.
-
Quan Tran, J. Firl (2013)
Modelling of traffic situations at urban intersections with probabilistic non-parametric regression2013 IEEE Intelligent Vehicles Symposium (IV)
-
Ruijie He, E. Brunskill, N. Roy (2014)
Efficient Planning under Uncertainty with Macro-actionsJ. Artif. Intell. Res., 40
-
Taekhee Lee, Young Kim (2016)
Massively parallel motion planning algorithms under uncertainty using POMDPThe International Journal of Robotics Research, 35
-
T. Bandyopadhyay, K. Won, Emilio Frazzoli, David Hsu, Wee Lee, D. Rus (2013)
Intention-Aware Motion Planning -
P. Fearnhead, Z. Liu (2007)
On‐line inference for multiple changepoint problemsJournal of the Royal Statistical Society: Series B (Statistical Methodology), 69
-
Wenda Xu, Junqing Wei, J. Dolan, Huijing Zhao, H. Zha (2012)
A real-time motion planner with trajectory optimization for autonomous vehicles2012 IEEE International Conference on Robotics and Automation
-
Michael Montemerlo, J. Becker, Suhrid Bhat, Hendrik Dahlkamp, D. Dolgov, S. Ettinger, D. Hähnel, T. Hildén, G. Hoffmann, Burkhard Huhnke, Doug Johnston, Stefan Klumpp, D. Langer, A. Levandowski, Jesse Levinson, J. Marcil, David Orenstein, Johannes Paefgen, I. Penny, A. Petrovskaya, M. Pflueger, Ganymed Stanek, David Stavens, Anton Vogt, S. Thrun (2008)
Junior: The Stanford entry in the Urban ChallengeJournal of Field Robotics, 25
-
H. Kurniawati, David Hsu, Wee Lee (2008)
SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces, 04
-
NE Toit, JW Burdick (2012)
Robot motion planning in dynamic, uncertain environmentsIEEE Transactions on Robotics, 28
-
David Silver, J. Veness (2010)
Monte-Carlo Planning in Large POMDPs -
Christopher Bishop (2006)
Pattern Recognition and Machine Learning (Information Science and Statistics) -
D. Ferguson, M. Darms, C. Urmson, Sascha Kolski (2008)
Detection, prediction, and avoidance of dynamic obstacles in urban environments2008 IEEE Intelligent Vehicles Symposium
-
J. Hardy, M. Campbell (2013)
Contingency Planning Over Probabilistic Obstacle Predictions for Autonomous Road VehiclesIEEE Transactions on Robotics, 29
-
(2008)
Probabilistic navigation in dynamic environment using Rapidly-exploring Random Trees and Gaussian Processes -
C. Piciarelli, G. Foresti (2006)
On-line trajectory clustering for anomalous events detectionPattern Recognit. Lett., 27
-
Georges Aoude, Brandon Luders, J. Joseph, N. Roy, J. How
Noname manuscript No. (will be inserted by the editor) Probabilistically Safe Motion Planning to Avoid Dynamic Obstacles with Uncertain Motion Patterns -
I. Miller, M. Campbell, D. Huttenlocher, Frank-Robert Kline, Aaron Nathan, Sergei Lupashin, Jason Catlin, B. Schimpf, Pete Moran, Noah Zych, Ephrahim Garcia, Mike Kurdziel, Hikaru Fujishima (2008)
Team Cornell's Skynet: Robust perception and planning in an urban environmentJournal of Field Robotics, 25
-
(2005)
Currently, he is an Associate Professor with the Department of Naval Architecture and Marine Engineering, University -
GS Aoude, BD Luders, JM Joseph, N Roy, JP How (2013)
Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patternsAutonomous Robots, 35
-
C. Papadimitriou, J. Tsitsiklis (1987)
The Complexity of Markov Decision ProcessesMath. Oper. Res., 12
-
Q. Tran, J. Firl (2014)
Online maneuver recognition and multimodal trajectory prediction for intersection assistance using non-parametric regression2014 IEEE Intelligent Vehicles Symposium Proceedings
-
Alexander Cunningham, E. Galceran, R. Eustice, Edwin Olson (2015)
MPDM: Multipolicy decision-making in dynamic, uncertain environments for autonomous driving2015 IEEE International Conference on Robotics and Automation (ICRA)
-
(2013)
Experimental robotics: The 13th international symposium on experimental robotics (pp. 963–977) -
E. Galceran, Alexander Cunningham, R. Eustice, Edwin Olson (2017)
Multipolicy decision-making for autonomous driving via changepoint-based behavior prediction: Theory and experimentAutonomous Robots, 41
-
S. Niekum, Sarah Osentoski, C. Atkeson, A. Barto (2015)
Online Bayesian changepoint detection for articulated motion models2015 IEEE International Conference on Robotics and Automation (ICRA)
-
A. Somani, N. Ye, David Hsu, Wee Lee (2013)
DESPOT: Online POMDP Planning with RegularizationArXiv, abs/1609.03250
-
S. Brechtel, Tobias Gindele, R. Dillmann (2014)
Probabilistic decision-making under uncertainty for autonomous driving using continuous POMDPs17th International IEEE Conference on Intelligent Transportation Systems (ITSC)
-
Pete Trautman, Andreas Krause (2010)
Unfreezing the robot: Navigation in dense, interacting crowds2010 IEEE/RSJ International Conference on Intelligent Robots and Systems
-
Junqing Wei, J. Dolan, Jarrod Snider, B. Litkouhi (2011)
A point-based MDP for robust single-lane autonomous driving behavior under uncertainties2011 IEEE International Conference on Robotics and Automation
-
Tobias Gindele, S. Brechtel, R. Dillmann (2015)
Learning Driver Behavior Models from Traffic Observations for Decision Making and PlanningIEEE Intelligent Transportation Systems Magazine, 7
-
S. Candido, James Davidson, S. Hutchinson (2010)
Exploiting domain knowledge in planning for uncertain robot systems modeled as POMDPs2010 IEEE International Conference on Robotics and Automation
-
Jeong Choi, Gyuho Eoh, Jimin Kim, Y. Yoon, Jung-Hee Park, Beomhee Lee (2010)
Analytic collision anticipation technology considering agents' future behavior2010 IEEE/RSJ International Conference on Intelligent Robots and Systems
-
(2011)
Probabilistic MDPbehavior planning for cars -
S. Niekum, Sarah Osentoski, C. Atkeson, A. Barto (2014)
CHAMP: Changepoint Detection Using Approximate Model Parameters -
D. Ferguson, T. Howard, M. Likhachev (2008)
Motion planning in urban environmentsJournal of Field Robotics, 25
-
Sebastian Thrun (1999)
Monte Carlo POMDPs -
N. Toit, J. Burdick (2010)
Robotic motion planning in dynamic, cluttered, uncertain environments2010 IEEE International Conference on Robotics and Automation
-
S. Petti, Thierry Fraichard (2005)
Safe motion planning in dynamic environments2005 IEEE/RSJ International Conference on Intelligent Robots and Systems
-
Omid Madani, S. Hanks, A. Condon (2003)
On the undecidability of probabilistic planning and related stochastic optimization problemsArtif. Intell., 147
-
T Bandyopadhyay, K Won, E Frazzoli, D Hsu, W Lee, D Rus (2013)
Proceedings of the international workshop on the algorithmic foundations of robotics, Springer tracts in advanced robotics
- Publisher
- Springer Journals
- Copyright
- Copyright © 2017 by Springer Science+Business Media New York
- Subject
- Engineering; Robotics and Automation; Artificial Intelligence (incl. Robotics); Computer Imaging, Vision, Pattern Recognition and Graphics; Control, Robotics, Mechatronics
- ISSN
- 0929-5593
- eISSN
- 1573-7527
- DOI
- 10.1007/s10514-017-9619-z
- Publisher site
- See Article on Publisher Site
Abstract
This paper reports on an integrated inference and decision-making approach for autonomous driving that models vehicle behavior for both our vehicle and nearby vehicles as a discrete set of closed-loop policies. Each policy captures a distinct high-level behavior and intention, such as driving along a lane or turning at an intersection. We first employ Bayesian changepoint detection on the observed history of nearby cars to estimate the distribution over potential policies that each nearby car might be executing. We then sample policy assignments from these distributions to obtain high-likelihood actions for each participating vehicle, and perform closed-loop forward simulation to predict the outcome for each sampled policy assignment. After evaluating these predicted outcomes, we execute the policy with the maximum expected reward value. We validate behavioral prediction and decision-making using simulated and real-world experiments.
Journal
Autonomous Robots – Springer Journals
Published: Feb 9, 2017