\r\nnavigation. It is a challenging task to ensure path optimality and

\r\nsafety in cluttered environments. We proposed an Environment

\r\nAware Dynamic Window Approach in this paper to cope with

\r\nthe issue. The method integrates environment characterization into

\r\nDynamic Window Approach (DWA). Two strategies are proposed

\r\nin order to achieve the integration. The local goal strategy guides

\r\nthe robot to move through openings before approaching the final

\r\ngoal, which solves the local minima problem in DWA. The adaptive

\r\ncontrol strategy endows the robot to adjust its state according

\r\nto the environment, which addresses path safety compared with

\r\nDWA. Besides, the evaluation shows that the path generated from

\r\nthe proposed algorithm is safer and smoother compared with

\r\nstate-of-the-art algorithms.","references":"[1] Hoy, Michael, Alexey S. Matveev, and Andrey V. Savkin, \u201cAlgorithms\r\nfor collision-free navigation of mobile robots in complex cluttered\r\nenvironments: a survey,\u201d Robotica, vol. 33, pp. 463-497, 2015.\r\n[2] Borenstein, Johann, and Yoram Koren, \u201cReal-time obstacle avoidance for\r\nfast mobile robots,\u201d IEEE Transactions on systems, Man, and Cybernetics,\r\nvol. 19, pp. 1179-1187, 1989.\r\n[3] Borenstein, Johann, and Yoram Koren, \u201cThe vector field histogram-fast\r\nobstacle avoidance for mobile robots,\u201d IEEE transactions on robotics and\r\nautomation, vol. 7, pp. 278-288, 1991.\r\n[4] Ulrich, Iwan, and Johann Borenstein, \u201cVFH+: Reliable obstacle avoidance\r\nfor fast mobile robots,\u201d in Proc. ICRA Conf., 1998, pp. 1572-1577.\r\n[5] Weerakoon, Tharindu, Kazuo Ishii, and Amir Ali Forough Nassiraei, \u201cAn\r\nartificial potential field based mobile robot navigation method to prevent\r\nfrom deadlock,\u201d Journal of Artificial Intelligence and Soft Computing\r\nResearch, vol. 5, pp. 189-203, 2015.\r\n[6] Demir, Mustafa, and Volkan Sezer, \u201cImproved follow the gap method for\r\nobstacle avoidance,\u201d in Advanced Intelligent Mechatronics (AIM), 2017,\r\npp. 1435-1440.\r\n[7] Simmons, Reid, \u201cThe curvature-velocity method for local obstacle\r\navoidance,\u201d in Proc. ICRA Conf., 1996, pp. 3375-3382.\r\n[8] Fox, Dieter, Wolfram Burgard, and Sebastian Thrun, \u201cThe dynamic\r\nwindow approach to collision avoidance,\u201d IEEE Robotics & Automation\r\nMagazine, vol. 4, pp. 23-33, 1997.\r\n[9] Ulrich, Iwan, and Johann Borenstein, \u201cVFH*: Local obstacle avoidance\r\nwith look-ahead verification,\u201d in Proc. ICRA Conf., 2000, pp. 2505-2511.\r\n[10] Chou, Chih-Chung, Feng-Li Lian, and Chieh-Chih Wang,\r\n\u201cCharacterizing indoor environment for robot navigation using velocity\r\nspace approach with region analysis and look-ahead verification,\u201d IEEE\r\nTransactions on Instrumentation and Measurement, vol. 60, pp. 442-451,\r\n2011.\r\n[11] Blanco, Jose Luis, Mauro Bellone, and Antonio Gimenez-Fernandez,\r\n\u201cTP-Space RRT: kinematic path planning of non-holonomic any-shape\r\nvehicles,\u201d International Journal of Advanced Robotic Systems, vol. 12,\r\npp. 55-63, 2015.\r\n[12] Devaurs D, Simon T and Corts J, \u201cOptimal path planning in complex\r\ncost spaces with sampling-based algorithms,\u201d IEEE Transactions on\r\nAutomation Science and Engineering, vol. 13, pp. 415-424, 2016.\r\n[13] Samaniego, Ricardo, Joaquin Lopez, and Fernando Vazquez, \u201cPath\r\nplanning for non-circular, non-holonomic robots in highly cluttered\r\nenvironments,\u201d Sensors, vol. 17, pp. 1876-1894, 2017.\r\n[14] Napoli, Michael E., Harel Biggie, and Thomas M. Howard, \u201cLearning\r\nmodels for predictive adaptation in state lattices,\u201d Field and Service\r\nRobotics, vol. 5, pp. 285-300, 2018.\r\n[15] Van Vliet, Lucas J., and Piet W. Verbeek, \u201cCurvature and bending energy\r\nin digitized 2D and 3D images,\u201d in Proceedings of the Scandinavian\r\nConference on Image Analysis, 1993, pp. 1403-1410.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 148, 2019"}