@inproceedings{Chen2017a, author = {Chen, Chao and Rickert, Markus and Knoll, Alois}, title = {Motion Planning under Perception and Control Uncertainties with Space Exploration Guided Heuristic Search}, booktitle = {Proceedings of the {IEEE} Intelligent Vehicles Symposium}, year = {2017}, month = jun, address = {Redondo Beach, CA, USA}, abstract = {Reliability and safety are extremely important for autonomous driving in real traffic scenarios. However, due to imperfect control and sensing, the actual state of the vehicle cannot be flawlessly predicted or measured, but estimated with uncertainty. Therefor, it is important to consider the execution risk advance in motion planning for a solution with a high success rate. The Space Exploration Guided Heuristic Search (SEHS) method is extended to deal with perception and control uncertainty in its two planning stages. First, the localization uncertainty is evaluated with a simple probabilistic robot model by the Space Exploration to find a path corridor with sufficient localization quality for the desired motion accuracy. Then, a trajectory controller is modeled with nonholonomic kinematics for the belief propagation of a robot state with primitive motions. The dynamic model and the control feedback are approximated in a close neighborhood of the reference trajectory. In this case, the Heuristic Search can propagate the state uncertainty as a normal distribution in the search tree to guarantee a high probability of safety and to achieve the required final accuracy. The belief-based SEHS is evaluated in several simulated scenarios. Compared to the basic SEHS method that assumes perfection, motions with higher execution successful rate are produced, especially the human-like behaviors for driving through narrow passages and precise parking. This confirms the major contribution of this work in exploiting the uncertainties for motion planning in autonomous driving.}, doi = {10.1109/IVS.2017.7995801}, keywords = {robotics, autonomous driving, path planning}, } @inproceedings{Chen2016a, author = {Chen, Chao and Rickert, Markus and Knoll, Alois}, title = {Combining Task and Motion Planning for Intersection Assistance Systems}, booktitle = {Proceedings of the {IEEE} Intelligent Vehicles Symposium}, pages = {1242--1247}, year = {2016}, month = jun, address = {Gothenburg, Sweden}, abstract = {A hybrid planning approach is developed for intersection assistance systems up to fully automated driving through intersections. Route planning, task planning and motion planning methods are integrated in a hierarchical planning framework to deal with the various information and constraints in different layers. The navigation agent provides a global driving direction at an intersection according to the selected route. The task planner decides a sequence of actions to accomplish the driving mission taking into consideration traffic rules and semantic conditions. The motion planner generates detailed trajectories to execute the tasks. Meanwhile, the task sequence and the motion trajectory are verified periodically against the actual traffic situation, and re-planning is triggered when necessary in the motion planning or task planning level. The hierarchical planning framework is evaluated in several intersection scenarios. The result shows that it can handle the complex planning problems with dynamic objects and provide a modular solution for automated driving that can be easily extended for different traffic rules and applications.}, doi = {10.1109/IVS.2016.7535549}, keywords = {autonomous driving}, } @phdthesis{, author = {Chen, Chao}, title = {Motion Planning for Nonholonomic Vehicles with Space Exploration Guided Heuristic Search}, year = {2016}, school = {Technische Universit{\"{a}}t M{\"{u}}nchen}, institution = {Fakult{\"{a}}t f{\"{u}}r Informatik}, location = {https://mediatum.ub.tum.de/1292197}, url = {https://mediatum.ub.tum.de/1292197}, } @inproceedings{Chen2015c, author = {Chen, Chao and Rickert, Markus and Knoll, Alois}, title = {Kinodynamic Motion Planning with Space-Time Exploration Guided Heuristic Search for Car-Like Robots in Dynamic Environments}, booktitle = {Proceedings of the {IEEE}/{RSJ} International Conference on Intelligent Robots and Systems ({IROS})}, pages = {2666--2671}, year = {2015}, month = sep, address = {Hamburg, Germany}, abstract = {The Space Exploration Guided Heuristic Search (SEHS) method solves the motion planning problem, especially for car-like robots, in two steps: a circle-based space exploration in the workspace followed by a circle-guided heuristic search in the configuration space. This paper extends this approach for kinodynamic planning in dynamic environments by performing the exploration in both space and time domains. Thus, a time-dependent heuristic is constructed to guide the search algorithm applying a kinodynamic vehicle model. Furthermore, the search step-size and state resolution are adapted incrementally to guarantee resolution completeness with a trade-off for efficiency. The performance of Space-Time Exploration Guided Heuristic Search (STEHS) approach is verified in two scenarios and compared with several search-based and sampling-based methods.}, doi = {10.1109/IROS.2015.7353741}, keywords = {autonomous driving, robotics}, url = {https://www.youtube.com/watch?v=AmyweePd1HU}, } @inproceedings{Chen2015a, author = {Chen, Chao and Rickert, Markus and Knoll, Alois}, title = {Path Planning with Orientation-Aware Space Exploration Guided Heuristic Search for Autonomous Parking and Maneuvering}, booktitle = {Proceedings of the {IEEE} Intelligent Vehicles Symposium ({IV})}, pages = {1148--1153}, year = {2015}, month = jul, address = {Seoul, South Korea}, abstract = {Due to the nonholonomic constraints of the vehicle kinematics, parking and maneuvering a car in a narrow clustered space are among the most challenging driving tasks. This paper introduces an extended version of Space Exploration Guided Heuristic Search (SEHS) method, called Orientation-Aware Space Exploration Guided Heuristic Search (OSEHS), to solve the path planning problems for parking and maneuvering. This method considers the orientation of a vehicle in the space exploration phase to achieve knowledge about driving directions. Such information is exploited later in the heuristic search phase to improve the planning efficiency in maneuvering scenarios. This approach is not bound to the specific domain knowledge about a parking or maneuvering task, but obtains the space dimension and orientation information through a generic exploration procedure. Therefore, it is convenient to integrate the maneuvering ability into a general SEHS motion planning framework. Experiments show that the OSEHS approach produces better results than common random-sampling methods and general heuristic search methods.}, doi = {10.1109/IVS.2015.7225838}, keywords = {autonomous driving, robotics}, } @inproceedings{ChenChao2015b, author = {Chen, Chao and Gaschler, Andre and Rickert, Markus and Knoll, Alois}, title = {Task Planning for Highly Automated Driving}, booktitle = {Proceedings of the {IEEE} Intelligent Vehicles Symposium ({IV})}, pages = {940--945}, year = {2015}, month = jul, address = {Seoul, South Korea}, abstract = {A hybrid planning approach is presented in this paper with the focus of integrating task planning and motion planning for highly automated driving. In the context of task planning, the vehicle and environment states are transformed from the continuous configuration space to a discrete state space. A planning problem is solved by a search algorithm for an optimal task sequence to reach the goal conditions in the symbolic space, regarding constraints such as space topology, place occupation, and traffic rules. Each task can be mapped to a specific driving maneuver and solved with a dedicated motion planning method in the continuous configuration space. The task planning approach not only bridges the gap between high-level navigation and low-level motion planning, but also provides a modular domain description that can be developed and verified individually. Our task planner for automated driving is evaluated in several scenarios with prior knowledge about the road-map and sensing range of the vehicle. Behavior that is otherwise complex to achieve is planned according to traffic rules and re-planned regarding the on-line perception.}, doi = {10.1109/IVS.2015.7225805}, keywords = {autonomous driving, robotics}, } @inproceedings{Chen2014a, author = {Chen, Chao and Rickert, Markus and Knoll, Alois}, title = {A Traffic Knowledge Aided Vehicle Motion Planning Engine Based on Space Exploration Guided Heuristic Search}, booktitle = {Proceedings of the IEEE Intelligent Vehicles Symposium}, pages = {535--540}, year = {2014}, month = jun, address = {Dearborn, MI, USA}, location = {Dearborn, Michigan, USA}, abstract = {A real-time vehicle motion planning engine is presented in this paper, with the focus on exploiting the prior and online traffic knowledge, e.g., predefined roadmap, prior environment information, behaviour-based motion primitives, within the space exploration guided heuristic search (SEHS) framework. The SEHS algorithm plans a kinodynamic vehicle motion in two steps: a geometric investigation of the free space, followed by a grid-free heuristic search employing primitive motions. These two procedures are generic and possible to take advantage of traffic knowledge. In this paper, the space exploration is supported by a roadmap and the heuristic search benefits from the behaviour-based primitives. Based on this idea, a light weighted motion planning engine is built, with the purpose to handle the traffic knowledge and the planning time in real-time motion planning. The experiments demonstrate that this SEHS motion planning engine is flexible and scalable for practical traffic scenarios with better results than the baseline SEHS motion planner regarding the provided traffic knowledge.}, doi = {10.1109/IVS.2014.6856458}, keywords = {autonomous driving, robotics}, } @inproceedings{, author = {Lenz, David and Minnerup, Pascal and Chen, Chao and Roth, Erwin}, title = {Mehrstufiges Planungskonzept f{\"{u}}r pilotierte Parkhausfunktionen}, booktitle = {30. VDI/VW-Gemeinschaftstagung "Fahrerassistenz und Integrierte Sicherheit 2014}, year = {2014}, location = {Wolfsburg, Germany}, keywords = {autonomous driving}, } @inproceedings{Chen2013a, author = {Chen, Chao and Rickert, Markus and Knoll, Alois}, title = {Combining Space Exploration and Heuristic Search in Online Motion Planning for Nonholonomic Vehicles}, booktitle = {Proceedings of the IEEE Intelligent Vehicles Symposium}, pages = {1307--1312}, year = {2013}, month = jun, address = {Gold Coast, Australia}, abstract = {This paper presents an efficient motion planning method for nonholonomic vehicles, which combines space exploration and heuristic search to achieve online performance. The space exploration employs simple geometric shapes to investigate the collision-free space for the dimension and topology information. Then, the heuristic search is guided by this knowledge to generate vehicle motions under kinodynamic constraints. The overall performance of this framework greatly benefits from the cooperation of these two simple generic algorithms in suitable domains, which sequentially handles the free-space information and kinodynamic constraints. Experimental results show that this method is able to generate motions for nonholonomic vehicles in a time frame of less than 100 milliseconds for the given problem settings. The contribution of this work is the development of a Space Exploration Guided Heuristic Search with a circle-path based heuristics and adaptable search step size. The approach is grid-free and able to plan nonholonomic vehicle motions under kinodynamic constraints.}, doi = {10.1109/IVS.2013.6629647}, keywords = {autonomous driving, robotics, path planning, motion planning}, } @inproceedings{Zhang2013a, author = {Zhang, Feihu and St{\"{a}}hle, Hauke and Chen, Chao and Buckl, Christian and Knoll, Alois}, title = {A Lane Marking Extraction Approach based on Random Finite Set Statistics}, booktitle = {Intelligent Vehicles Symposium (IV), 2013 IEEE}, year = {2013}, }