Mubbasir Kapadia
ABSTRACT
Path planning is a fundamental problem in many areas ranging from robotics and artificial intelligence to computer graphics and animation. While there is extensive literature for computing optimal, collision-free paths, there is little work that explores the satisfaction of spatial constraints between objects and agents at the global navigation layer. This paper presents a planning framework that satisfies multiple spatial constraints imposed on the path. The type of constraints specified could include staying behind a building, walking along walls, or avoiding the line of sight of patrolling agents. We introduce a hybrid environment representation that balances computational efficiency and discretization resolution, to provide a minimal, yet sufficient discretization of the search graph for constraint-aware navigation. An extended anytime-dynamic planner is used to compute constraint-aware paths, while efficiently repairing solutions to account for dynamic constraints. We demonstrate the benefits of our method on challenging navigation problems in complex environments for dynamic agents using combinations of hard and soft constraints, attracting and repelling constraints, on static obstacles and moving obstacles.
References
- Al Marzouqi, M., and Jarvis, R. 2011. Robotic covert path planning: A survey. In Robotics, Automation and Mechatronics (RAM), 2011 IEEE Conference on, 77--82.Google Scholar
- André, E., Bosch, G., Herzog, G., and Rist, T. 1986. Characterizing trajectories of moving objects using natural language path descriptions. In In: Proc. of the 7th ECAI, 1--8.Google Scholar
- Arkin, R. 1987. Motor schema based navigation for a mobile robot: An approach to programming by behavior. In Robotics and Automation. Proceedings. 1987 IEEE International Conference on, vol. 4, 264--271.Google ScholarCross Ref
- Bhattacharya, S., Likhachev, M., and Kumar, V. 2012. Topological constraints in search-based robot path planning. Auton. Robots 33, 3, 273--290.Google ScholarCross Ref
- Bhattacharya, S., Likhachev, M., and Kumar, V. 2012. Search-based path planning with homotopy class constraints in 3d. In AAAI.Google Scholar
- Dechter, R., and Pearl, J. 1985. Generalized best-first search strategies and the optimality af a*. J. ACM 32, 3, 505--536. Google ScholarDigital Library
- Geraerts, R. 2010. Planning short paths with clearance using explicit corridors. In ICRA, IEEE, 1997--2004.Google Scholar
- Goldenstein, S., Karavelas, M., Metaxas, D., Guibas, L., Aaron, E., and Goswami, A., 2001. Scalable nonlinear dynamical systems for agent steering and crowd simulation.Google Scholar
- Hart, P., Nilsson, N., and Raphael, B. 1968. A formal basis for the heuristic determination of minimum cost paths. Systems Science and Cybernetics, IEEE Transactions on 4, 2, 100--107.Google Scholar
- Hart, P. E., Nilsson, N. J., and Raphael, B. 1972. Correction to "a formal basis for the heuristic determination of minimum cost paths". SIGART Bull., 37, 28--29. Google ScholarDigital Library
- Helbing, D., and Molnár, P. 1995. Social force model for pedestrian dynamics. Phys. Rev. E 51, 5 (May), 4282--4286.Google ScholarCross Ref
- Hernandez, E., Carreras, M., Galceran, E., and Ridao, P. 2011. Path planning with homotopy class constraints on bathymetric maps. In OCEANS - Europe.Google Scholar
- Kallmann, M. 2010. Shortest paths with arbitrary clearance from navigation meshes. In ACM SIGGRAPH/Eurographics SCA, 159--168. Google ScholarDigital Library
- Kapadia, M., and Badler, N. I. 2013. Navigation and steering for autonomous virtual humans. Wiley Interdisciplinary Reviews: Cognitive Science, n/a--n/a.Google Scholar
- Kapadia, M., Singh, S., Hewlett, W., and Faloutsos, P. 2009. Egocentric affordance fields in pedestrian steering. In Proceedings of the 2009 symposium on Interactive 3D graphics and games, ACM, New York, NY, USA, I3D '09, 215--223. Google ScholarDigital Library
- Kapadia, M., Singh, S., Hewlett, W., Reinman, G., and Faloutsos, P. 2012. Parallelized egocentric fields for autonomous navigation. The Visual Computer, 1--19. 10.1007/s00371-011-0669-5.Google Scholar
- Kapadia, M., Beacco, A., Garcia, F., Reddy, V., Pelechano, N., and Badler, N. I. 2013. Multi-domain real-time planning in dynamic environments. In Proceedings of the 12th ACM SIGGRAPH/Eurographics Symposium on Computer Animation, ACM, New York, NY, USA, SCA '13, 115--124. Google ScholarDigital Library
- Koenig, S., and Likhachev, M. 2002. D* Lite. In National Conf. on AI, AAAI, 476--483. Google ScholarDigital Library
- Likhachev, M., Gordon, G. J., and Thrun, S. 2003. ARA*: Anytime A* with Provable Bounds on Sub-Optimality. In NIPS.Google Scholar
- Likhachev, M., Ferguson, D. I., Gordon, G. J., Stentz, A., and Thrun, S. 2005. Anytime Dynamic A*: An Anytime, Replanning Algorithm. In ICAPS, 262--271.Google Scholar
- Mononen, M., 2009. Recast: Navigation-mesh construction toolset for games. http://code.google.com/p/recastnavigation/.Google Scholar
- Paris, S., Pettr, J., and Donikian, S. 2007. Pedestrian reactive navigation for crowd simulation: a predictive approach. Comput. Graph. Forum 26, 3, 665--674.Google ScholarCross Ref
- Pelechano, N., Allbeck, J. M., and Badler, N. I. 2007. Controlling individual agents in high-density crowd simulation. In Proceedings of the 2007 ACM SIGGRAPH/Eurographics symposium on Computer animation, Eurographics Association, Aire-la-Ville, Switzerland, Switzerland, SCA '07, 99--108. Google ScholarDigital Library
- Pelechano, N., Allbeck, J. M., and Badler, N. I. 2008. Virtual Crowds: Methods, Simulation, and Control. Synthesis Lectures on Computer Graphics and Animation. Morgan & Claypool Publishers. Google ScholarDigital Library
- Phillips, M., Hwang, V., Chitta, S., and Likhachev, M. 2013. Learning to plan for constrained manipulation from demonstrations.Google Scholar
- Reynolds, C. 1999. Steering Behaviors for Autonomous Characters. In Game Developers Conference 1999.Google Scholar
- Schuerman, M., Singh, S., Kapadia, M., and Faloutsos, P. 2010. Situation agents: agent-based externalized steering logic. Comput. Animat. Virtual Worlds 21 (May), 267--276. Google ScholarDigital Library
- Shimoda, S., Kuroda, Y., and Iagnemma, K. 2005. Potential field navigation of high speed unmanned ground vehicles on uneven terrain. Robotics and Automation, 2005. ICRA 2005. Proceedings of the 2005 IEEE International Conference on, 2828--2833.Google Scholar
- Shoulson, A., Marshak, N., Kapadia, M., and Badler, N. I. 2013. Adapt: the agent development and prototyping testbed. In Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, ACM, New York, NY, USA, I3D '13, 9--18. Google ScholarDigital Library
- Singh, S., Kapadia, M., Hewlett, B., Reinman, G., and Faloutsos, P. 2011. A modular framework for adaptive agent-based steering. In Symposium on Interactive 3D Graphics and Games, ACM, New York, NY, USA, I3D '11, 141--150 [email protected] Google ScholarDigital Library
- Singh, S., Kapadia, M., Reinman, G., and Faloutsos, P. 2011. Footstep navigation for dynamic crowds. Computer Animation and Virtual Worlds 22, 2-3, 151--158. Google ScholarDigital Library
- Sturtevant, N. 2012. Benchmarks for grid-based pathfinding. Transactions on Computational Intelligence and AI in Games 4, 2, 144--148.Google ScholarCross Ref
- Treuille, A., Cooper, S., and Popović, Z. 2006. Continuum crowds. ACM Trans. Graph. 25, 3, 1160--1168. Google ScholarDigital Library
- van den Berg, J., Lin, M. C., and Manocha, D. 2008. Reciprocal velocity obstacles for real-time multi-agent navigation. In IEEE International Conference on Robotics and Automation, IEEE, 1928--1935.Google Scholar
- Warren, C. 1989. Global path planning using artificial potential fields. In Proceedings of IEEE ICRA, vol. 1, 316--321.Google Scholar
- Warren, C. 1990. Multiple robot path coordination using artificial potential fields. In Proceedings of IEEE ICRA, vol. 1, 500--505.Google Scholar
- Xu, Y. D., and Badler, N. 2000. Algorithms for generating motion trajectories described by prepositions. In Computer Animation 2000. Proceedings, 30--35. Google ScholarDigital Library
Index Terms
Constraint-Aware Navigation in Dynamic Environments
Reviews
Fernando Santos Osorio
Kapadia et al. present a path planning method, mostly oriented to game applications such as non-player characters/autonomous agents, that is based on the anytime dynamic A* (AD*) planner [1]. The main improvements are related to the adoption of hybrid graphs to represent the environment, combining a coarse representation-the so-called “highways,” with few nodes and allowing fast planning-with a detailed representation-a dense graph with detailed triangulation of free spaces, and precise but slower planning. The authors also propose adding constraints that can influence the trajectories, with weights defining a multiplier field (continuous potential fields with attractors/repellants), generated from simple declarative prepositions (for example, In/Not In: Front, Between, LineOfSight). As the planner is based on AD*, it can deal with dynamic constraints and obstacles, interleaving planning with navigation execution. On the other side, as the planner uses constraints and hybrid graphs (with “highways”), the planned path is not guaranteed to be optimal. The proposed approach improves the well-known path planning AD* algorithm, allowing it to define constraints and using an optimized hybrid representation of the environment, adding some interesting features to the original algorithm. The authors also present practical results that demonstrate the main advantages of their proposed approach. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments