{"type":"ScholarlyArticle","title":"Motion Planning Under Uncertainty with Complex Agents and Environments via Hybrid Search (Extended Abstract)","authors":[{"name":"Daniel Strawser","slug":"daniel-strawser","given":"Daniel","family":"Strawser","affiliation":"Massachusetts Institute of Technology"},{"name":"Brian Williams","slug":"brian-williams","given":"Brian","family":"Williams","affiliation":"Massachusetts Institute of Technology"}],"abstract":"As autonomous systems tackle more real-world situations, mission success oftentimes cannot be guaranteed and the planner must reason about the probability of failure.  Unfortunately, computing a trajectory that satisfies mission goals while constraining the probability of failure is difficult because of the need to reason about complex, multidimensional probability distributions.  Recent methods have seen success using chance-constrained, model-based planning.  We argue there are two main drawbacks to these approaches.  First, current methods suffer from an inability to deal with expressive environment models such as 3D non-convex obstacles.  Second, most planners rely on considerable simplifications when computing trajectory risk including approximating the agent's dynamics, geometry, and uncertainty.  We apply hybrid search to the risk-bound, goal-directed planning problem.  The hybrid search consists of a region planner and a trajectory planner.  The region planner makes discrete choices by reasoning about geometric regions that the agent should visit in order to accomplish its mission.  In formulating the region planner, we propose landmark regions that help produce obstacle-free paths.  The region planner passes paths through the environment to a trajectory planner; the task of the trajectory planner is to optimize trajectories that respect the agent's dynamics and the user's desired risk of mission failure.  We discuss three approaches to modeling trajectory risk: a CDF-based approach, a sampling-based collocation method, and an algorithm named Shooting Method Monte Carlo.  A variety of 2D and 3D test cases are presented in the full paper including a linear case, a Dubins car model, and an underwater autonomous vehicle.  The method is shown to outperform other methods in terms of speed and utility of the solution.  Additionally, the models of trajectory risk are shown to better approximate risk in simulation.","doi":"10.24963/ijcai.2023/792","url":"https://ijcai.org/proceedings/2023/792","pdf":"https://ijcai.org/proceedings/2023/0792.pdf","markdown":"https://ijcai.org/proceedings/2023/792.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/792","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Journal Track","track":"Journal Track","number":792,"pages":{"first":6969,"last":6973},"keywords":["Planning and Scheduling: PS: Robot planning","Robotics: ROB: Motion and path planning","Planning and Scheduling: PS: Planning under uncertainty"],"videos":[],"references":[{"position":1,"raw":"[Blackmore et al., 2011] Lars Blackmore, Masahiro Ono, and Brian C. Williams. Chance-constrained optimal path planning with obstacles. IEEE Trans. Robotics, 27(6):1080-1094, 2011.","title":"Chance-constrained optimal path planning with obstacles","authors":"Blackmore","year":"2011","venue":"IEEE Trans. Robotics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Deits and Tedrake, 2015] Robin Deits and Russ Tedrake. Computing Large Convex Regions of Obstacle-Free Space Through Semidefinite Programming, pages 109-124. Springer International Publishing, Cham, 2015.","title":"Computing Large Convex Regions of Obstacle-Free Space Through Semidefinite Programming","authors":"Tedrake Deits, Robin Deits, Russ Tedrake","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Faust et al., 2018] Aleksandra Faust, Oscar Ramirez, Marek Fiser, Ken Oslund, Anthony Francis, James Davidson, and Lydia Tapia. PRM-RL: Long-range robotic navigation tasks by combining reinforcement learning and sampling- based planning. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, pages 5113-5120, Brisbane, Australia, 2018.","title":"PRM-RL: Long-range robotic navigation tasks by combining reinforcement learning and samplingbased planning","authors":"Aleksandra Faust, Oscar Ramirez, Marek Fiser, Ken Oslund, Anthony Francis, James Davidson, Lydia Tapia","year":"2018","venue":"2018 IEEE International Conference on Robotics and Automation, ICRA 2018","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fernandez-Gonzalez et al., 2018] Enrique Fernandez- Gonzalez, Brian C. Williams, and Erez Karpas. Scotty- Activity: Mixed Discrete-Continuous Planning with Convex Optimization. Journal of Artificial Intelligence Resesearch (JAIR), 62:579-664, 2018.","title":"Scotty-Activity: Mixed Discrete-Continuous Planning with Convex Optimization","authors":"Enrique Fernandez-Gonzalez, Brian C Williams, Erez Karpas","year":"2018","venue":"Journal of Artificial Intelligence Resesearch (JAIR)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Luders et al., 2010] Brandon Luders, Mangal Kothari, and Jonathan P. How. Chance-constrained RRT for proba- bilistic robustness to environmental uncertainty. In AIAA Guidance, Navigation, and Control Conference (GNC), Toronto, Canada, August 2010.","title":"How. Chance-constrained RRT for probabilistic robustness to environmental uncertainty","authors":"Brandon Luders, Mangal Kothari, Jonathan P","year":"2010","venue":"AIAA Guidance, Navigation, and Control Conference (GNC)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ono et al., 2013] Masahiro Ono, Brian C. Williams, and Lars Blackmore. Probabilistic Planning for Continuous Dynamic Systems under Bounded Risk. Journal of Artifi- cial Intelligence Research (JAIR), 46:511-577, 2013.","title":"Probabilistic Planning for Continuous Dynamic Systems under Bounded Risk","authors":"Masahiro Ono, Brian C Williams, Lars Blackmore","year":"2013","venue":"Journal of Artificial Intelligence Research (JAIR)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Patil et al., 2012] Sachin Patil, Jur van den Berg, and Ron Alterovitz. Estimating probability of collision for safe mo- tion planning under Gaussian motion and sensing uncer- tainty. In IEEE International Conference on Robotics and Automation, ICRA 2012, St.","title":"Estimating probability of collision for safe motion planning under Gaussian motion and sensing uncertainty","authors":"Sachin Patil, Jur Van Den, Ron Berg, Alterovitz","year":null,"venue":"IEEE International Conference on Robotics and Automation, ICRA 2012","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"Paul, Minnesota, USA, 2012.","title":null,"authors":"Minnesota Paul","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Strawser and Williams, 2022] Daniel Strawser and Brian C. Williams. Motion Planning Under Uncertainty with Com- plex Agents and Environments via Hybrid Search. Journal of Artificial Intelligence Research (JAIR), 75:1-81, 2022.","title":"Motion Planning Under Uncertainty with Complex Agents and Environments via Hybrid Search","authors":"Daniel Strawser, Brian C Williams","year":"2022","venue":"Journal of Artificial Intelligence Research (JAIR)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}