{"id":181,"date":"2015-08-07T21:10:33","date_gmt":"2015-08-07T13:10:33","guid":{"rendered":"https:\/\/www.cognav.net\/?p=181"},"modified":"2015-08-07T21:15:03","modified_gmt":"2015-08-07T13:15:03","slug":"%e5%9f%ba%e4%ba%8eoccupancy-grids%e7%9a%84%e4%ba%8c%e7%bb%b4%e8%af%ad%e4%b9%89%e5%88%b6%e5%9b%be","status":"publish","type":"post","link":"https:\/\/braininspirednavigation.com\/?p=181","title":{"rendered":"\u57fa\u4e8eOccupancy Grids\u7684\u4e8c\u7ef4\u8bed\u4e49\u5236\u56fe"},"content":{"rendered":"

\n\t\u57fa\u4e8eOccupancy Grids\u7684\u4e8c\u7ef4\u8bed\u4e49\u5236\u56fe<\/span><\/span><\/span>\n<\/p>\n

\n\t2D Semantic Mapping on Occupancy Grids<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t      \u8fd1\u5e74\u6765\uff0c\u5b66\u8005\u4eec\u5bf9\u5ba4\u5185\u77e2\u91cf\u5730\u56fe\u6280\u672f\u5f00\u5c55\u4e86\u5927\u91cf\u7814\u7a76\u5de5\u4f5c\uff0c\u5df2\u7ecf\u5728\u8bb8\u591a\u65b9\u9762\u5f97\u5230\u4e86\u5f88\u597d\u7684\u5e94\u7528\u3002SLAM\u65b9\u6cd5\u80fd\u591f\u751f\u6210\u5168\u5c40\u4e00\u81f4\u7684\u77e2\u91cf\u5730\u56fe\u3002\u5c3d\u7ba1\u8fd9\u6837\u7684\u5730\u56fe\u63cf\u8ff0\u4e86\u73af\u5883\u57fa\u672c\u7684\u4fe1\u606f\u5e76\u80fd\u591f\u652f\u6301\u5bfc\u822a\uff0c\u4f46\u4ecd\u7136\u7f3a\u4e4f\u73af\u5883\u7684\u66f4\u9ad8\u5c42\u62bd\u8c61\u7684\u8bed\u4e49\u4fe1\u606f\u6216\u8005\u4eba\u4eec\u8ba4\u77e5\u7684\u8bed\u4e49\u4fe1\u606f\uff0c\u4f8b\u5982\u5efa\u7b51\u7ed3\u6784\u7684\u7c7b\u522b\u3001\u8fde\u901a\u6027\u7b49\u3002\u672c\u6587\u4e2d\u63d0\u51fa\u4e86\u4e00\u79cd\u65b0\u7684\u6982\u7387\u65b9\u6cd5\u57fa\u4e8e\u5168\u8986\u76d6\u7684\u7f51\u683c\u56fe\u5206\u6790\u6f5c\u5728\u7684\u8bed\u4e49\u4e16\u754c\u6a21\u578b\u3002\u8be5\u6a21\u578b\u662f\u7531\u6807\u51c6\u7684SLAM\u65b9\u6cd5\u6240\u4ea7\u751f\u3002\u6587\u4e2d\u7684\u65b9\u6cd5\u4eff\u771f\u4e86\u4e00\u79cd\u9a6c\u5c14\u53ef\u592b\u94fe\u4ece\u7ed9\u5b9a\u8f93\u5165\u5730\u56fe\u7684\u8bed\u4e49\u4e16\u754c\u6a21\u578b\u6982\u7387\u5206\u5e03\u4ea7\u751f\u6837\u672c\u3002\u5b9e\u9a8c\u8868\u660e\u8be5\u65b9\u6cd5\u662f\u6709\u6548\u7684\uff0c\u80fd\u591f\u6b63\u786e\u6355\u83b7\u5230\u4e0d\u786e\u5b9a\u6027\u3002<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t      \u5178\u578b\u7684\u8bed\u4e49\u6982\u5ff5\uff0c\u6bd4\u5982\u623f\u95f4\u3001\u8d70\u5eca\u3001\u7a7a\u95f4\u5173\u7cfb\uff08\u90bb\u63a5\u3001\u8fde\u901a\uff09\u3001\u5176\u4ed6\u5c5e\u6027\uff08\u5982\u77e9\u5f62\uff09\u3002\u8fd9\u4e9b\u8bed\u4e49\u4fe1\u606f\u6709\u52a9\u4e8e\u6784\u5efa\u5730\u56fe\u3002\u867d\u7136\u8bed\u4e49\u673a\u5668\u4eba\u5236\u56fe\u6ca1\u6709\u50cf\u77e2\u91cf\u6216\u62d3\u6251\u5236\u56fe\u4e00\u6837\u5f97\u5230\u5e7f\u6cdb\u7814\u7a76\uff0c\u4f46\u4e5f\u6709\u4e00\u4e9b\u91cd\u8981\u7684\u8d21\u732e\u3002 \u6587\u732e\u301011\u3011\u4e2d\u7684\u65b9\u6cd5\u4f5c\u4e3a\u8bb8\u591a\u79cd\u8bed\u4e49\u5236\u56fe\u65b9\u6cd5\u7684\u5148\u9a71\uff0c\u7ed3\u5408\u4e86\u7f51\u683c\u548c\u62d3\u6251\u5236\u56fe\u65b9\u6cd5\u80fd\u591f\u540c\u65f6\u83b7\u5f97\u9ad8\u7cbe\u5ea6\u3001\u4e00\u81f4\u6027\u7684\u77e2\u91cf\u56fe\u548c\u6709\u6548\u62d3\u6251\u56fe\u3002 Wolf and Sukhatme [14] \u63d0\u51fa\u4e86\u4f7f\u7528\u9690\u9a6c\u5c14\u53ef\u592b\u6a21\u578b\u548c\u652f\u6301\u5411\u91cf\u673a\u6765\u89e3\u51b3\u5730\u5f62\u5236\u56fe\u548c\u57fa\u4e8e\u6d3b\u52a8\u5236\u56fe\u4e2d\u6240\u5b58\u5728\u7684\u95ee\u9898\u3002\u6587\u732e [10], [2] \u548c [3]\u5229\u7528\u8bed\u4e49\u6807\u7b7e\u6765\u6807\u6ce8\u4f4d\u7f6e\u548c\u533a\u57df\u3002 Douillard\u7b49\u4eba\u63d0\u51fa\u4f7f\u7528\u6761\u4ef6\u968f\u673a\u573a\uff08conditional random fields\uff09\u6784\u5efa\u5ba4\u5916\u73af\u5883\u5bf9\u8c61\u5730\u56fe\u3002\u6b64\u5916\uff0c\u4e00\u4e9b\u5b66\u8005\u8fd8\u63d0\u51fa\u4e86\u5229\u7528\u8bed\u4e49\u6807\u6ce8\u73af\u5883\u7ed3\u6784\u7684\u65b9\u6cd5\uff0c\u6bd4\u5982\u5ba4\u5916\u73af\u5883\u7684\u9053\u8def\uff08traversable terrain\uff09\u3001\u5ba4\u5185\u73af\u5883\u4e2d\u7684\u5899\u3001\u5929\u82b1\u677f\u548c\u95e8\u3002\u6bd4\u8f83\u5178\u578b\u7684\u4f8b\u5b50\u5982[8], [12], [6] \u548c[9]\u3002<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t       In recent years, techniques for building metric maps of indoor environments have been intensely studied, and they perform very well in noumerous applications. Simultaneous Localization and Mapping (SLAM) methods produce globally consistent, metric maps of the explored environment. Although such maps describe how the environment looks like and can be used for navigation, there exist no abstracted semantic concepts that explain the environment on a higher level or in a more natural way (as we humans do), such as, what kind of structure and connectivity the environment possesses. In this paper, we propose a new probabilistic method to analyze the underlying semantic world model based on an occupancy grid map, which is generated by a standard SLAM process. Our approach simulates a Markov Chain that produces samples from the distribution of probable semantic world models given an input map. Experiments show that our approach is effective and correctly captures the uncertainty.<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t      Typical semantic concepts, such as rooms and corridors, or spatial relations like adjacency, connectivity via doors, or properties like rectangularity that – if known to be relevant to the given environment – could help to build the maps in the first place. Although semantic robot mapping has not been as intensively studied as metric or topological mapping, some notable conbtributions have already been made. As an early predecessor of many semantic mapping approaches one might consider [11], which combined the grid-based and topological mapping to gain both of accuracy\/consistency (metric) and efficiency (topological), the latter effectively by means of abstraction. Wolf and Sukhatme [14] proposed to use hidden Markov models and support vector machines to tackle the problem of terrain mapping and activity-based mapping. [10], [2] and [3] used semantic labels to annotate the places and regions explored by a mobile robot. Douillard et. al. proposed to use conditional random fields to build object-type maps of outdoor environments. Other examples of assigning semantic labels to perceived objects in the explored environments are presented in [7] and [13]. In addition, methods, which semantically annotate the structure of the environments, like traversable terrain in outdoor environments or walls, cellings and door in indoor environments, have also been proposed. Some remarkable examples are [8], [12], [6] and [9].<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t       \u8fd9\u79cd\u62bd\u8c61\u6a21\u578b\u7c7b\u4f3c\u4e8e\u573a\u666f\u56fe\uff0c\u8fd9\u79cd\u7ed3\u6784\u5e7f\u6cdb\u5e94\u7528\u5728\u8ba1\u7b97\u673a\u56fe\u5f62\u5b66\u9886\u57df\u4e2d\u3002\u5728\u4f8b\u5b50\u4e2d\u7684\u56fe\uff08\u5982\u56fe1d\u6240\u793a\uff09\u7531\u623f\u95f4\u548c\u95e8\u7ec4\u6210\uff0c\u53ef\u4ee5\u663e\u793a\u4e3a\u4e00\u79cd\u7ecf\u5178\u7684\u697c\u5c42\u5e73\u9762\u56fe\uff0c\u5982\u56fe1b\u6240\u793a\u3002\u8fde\u901a\u4fe1\u606f\u8868\u793a\u4e3a\u4e00\u79cd\u62d3\u6251\u56fe\uff0c\u5982\u56fe1c\u6240\u793a\uff0c\u80fd\u591f\u7528\u4e8e\u5bfc\u822a\u5e94\u7528\u3002<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t      This abstract model has a form similar to a scene graph, a structure which is widely used in computer graphics. The graph (see Figure 1d) in our case consists of rooms and doorways connecting the rooms and can be visualized as a classical floor plan (see Figure 1b). As a by-product, the connectivity information is represented as a topological map (see Figure 1c) which is of great help for navigation purpose.<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t\"\"\"\"\n<\/p>\n

\n\tFigure 1: a) A simplified occupancy grid map: Unexplored area is drawn in blue, free space is drawn in white. Occupied area is drawn in black. b) A possible floor plan represented as a scene graph (W): The world is divided into four rooms and the corresponding unexplored area. Connectivity is given by the color of walls: the color cyan indicates connected, which means there is a door (cyan dotted) between two rooms; the color orange means adjacent, which means that two rooms are neighbor and do not connect themselves through a door; the color black stands for a boundary wall. The detected main orientations of walls are illustrated by violet arrows. c) The connectivity information represented as a topological map of world W: Green circles indicate room centers, and red lines connect the room centers and their corresponding doors. d) The semantic description of the world in form of the scene graph: Directed links connect nodes. The dashed lines indicate connectivity which is represented as a topological map in c). Like room 4, each room has three child nodes: walls, free space, and doors. Note that the lowest level of node in the tree structure is the grid cell that either belongs to a wall, free space or a door.<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t\"\"\"\"\"\"\n<\/p>\n

\n\tFigure 7: One example of an offline result. a) An occupancy grid map M [5]. b) The classified map CM with three intensity values (black=wall, grey=unexplored, white=free). c) The analyzed world W (black=boundary wall, orange=adjacent wall, gray=unknown, white=free, cyan=door). d) Boundary walls (blue), adjacent walls (orange) and doors (cyan) of the world W drawn into the map. e) Generate the topological map using the connectivity information. f) The resulting topological map (green circles=room centers).<\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\tLiu Z, Chen D, Von Wichert G. 2D Semantic Mapping on Occupancy Grids[C]\/\/ Robotics; Proceedings of ROBOTIK 2012; 7th German Conference onVDE, 2012:1-6.<\/span><\/span><\/span><\/span>\n<\/p>\n

\n\t \n<\/p>\n

\n\t[2] S. Friedman, H. Pasula, and D. Fox. Voronoi random fields: Extracting the topological structure of indoor environments via place labeling. In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI), 2007.<\/span><\/span><\/span>\n<\/p>\n

\n\t[3] N. Goerke and S. Braun. Building semantic annotated maps by mobile robots. In Proceedings of the Conference Towards Autonomous Robotic Systems, Londonderry, UK, 2009.<\/span><\/span><\/span>\n<\/p>\n

\n\t[6] A.K. Krishnan and K.M. Krishna. A visual exploration algorithm using semantic cues that constructs image based hybrid maps. In IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1316 –1321, Oct. 2010.<\/span><\/span><\/span>\n<\/p>\n

\n\t[8] A. Nüchter and J. Hertzberg. Towards semantic maps for mobile robots. Robotics and Autonomous Systems, 56(11):915–926, 2008.<\/span><\/span><\/span>\n<\/p>\n

\n\t[9] M. Persson, T. Duckett, C. Valgren, and A. Lilienthal. Probabilistic semantic mapping with a virtual sensor for building\/ nature detection. In International Symposium on Computational Intelligence in Robotics and Automation, pages 236 –242, June 2007.<\/span><\/span><\/span>\n<\/p>\n

\n\t[10] A. Pronobis, P. Jensfelt, K. Sjöö, H. Zender, G. M. Kruijff, O. M. Mozos, and W. Burgard. Semantic modelling of space. In Cognitive Systems, volume 8 of Cognitive Systems Monographs, pages 165–221. Springer Berlin Heidelberg, 2010.<\/span><\/span><\/span>\n<\/p>\n

\n\t[11] S. Thrun and A. Bücken. Integrating grid-based and topological maps for mobile robot navigation. In Proceedings of the AAAI Thirteenth National Conference on Artificial Intelligence, Portland, Oregon, 1996.<\/span><\/span><\/span>\n<\/p>\n

\n\t[12] Jingchen Tong, Dong Chen, Yan Zhuang, and Wei Wang. Mobile robot indoor semantic mapping using 3d laser scanning and monocular vision. In 8th World Congress on Intelligent Control and Automation (WCICA), pages 1212 –1217, July 2010.<\/span><\/span><\/span>\n<\/p>\n

\n\t[14] D.F. Wolf and G.S. Sukhatme. Semantic mapping using mobile robots. IEEE Transactions on Robotics, 24(2):245–258, 2008.<\/span><\/span><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

\u57fa\u4e8eOccupancy Grids\u7684\u4e8c\u7ef4\u8bed\u4e49\u5236\u56fe 2D Semantic Mapping on Occupancy Grids         \u8fd1\u5e74\u6765\uff0c\u5b66\u8005\u4eec\u5bf9\u5ba4\u5185\u77e2\u91cf\u5730\u56fe\u6280\u672f\u5f00\u5c55\u4e86\u5927\u91cf\u7814\u7a76\u5de5\u4f5c\uff0c\u5df2\u7ecf\u5728\u8bb8\u591a\u65b9\u9762\u5f97\u5230\u4e86\u5f88\u597d\u7684\u5e94\u7528\u3002SLAM\u65b9\u6cd5\u80fd\u591f\u751f\u6210\u5168\u5c40\u4e00\u81f4\u7684\u77e2\u91cf\u5730\u56fe\u3002\u5c3d\u7ba1\u8fd9\u6837\u7684\u5730\u56fe\u63cf\u8ff0\u4e86\u73af\u5883\u57fa\u672c\u7684\u4fe1\u606f\u5e76\u80fd\u591f\u652f\u6301\u5bfc\u822a\uff0c\u4f46\u4ecd\u7136\u7f3a\u4e4f\u73af\u5883\u7684\u66f4\u9ad8\u5c42\u62bd\u8c61\u7684\u8bed\u4e49\u4fe1\u606f\u6216\u8005\u4eba\u4eec\u8ba4\u77e5\u7684\u8bed\u4e49\u4fe1\u606f\uff0c\u4f8b\u5982\u5efa\u7b51\u7ed3\u6784\u7684\u7c7b\u522b\u3001\u8fde\u901a\u6027\u7b49\u3002\u672c\u6587\u4e2d\u63d0\u51fa\u4e86\u4e00\u79cd\u65b0\u7684\u6982\u7387\u65b9\u6cd5\u57fa\u4e8e\u5168\u8986\u76d6\u7684\u7f51\u683c\u56fe\u5206\u6790\u6f5c\u5728\u7684\u8bed\u4e49\u4e16\u754c\u6a21\u578b\u3002\u8be5\u6a21\u578b\u662f\u7531\u6807\u51c6\u7684SLAM\u65b9\u6cd5\u6240\u4ea7\u751f\u3002\u6587\u4e2d\u7684\u65b9\u6cd5\u4eff\u771f\u4e86\u4e00\u79cd\u9a6c\u5c14\u53ef\u592b\u94fe\u4ece\u7ed9\u5b9a\u8f93\u5165\u5730\u56fe\u7684\u8bed\u4e49\u4e16\u754c\u6a21\u578b\u6982\u7387\u5206\u5e03\u4ea7\u751f\u6837\u672c\u3002\u5b9e\u9a8c\u8868\u660e\u8be5\u65b9\u6cd5\u662f\u6709\u6548\u7684\uff0c\u80fd\u591f\u6b63\u786e\u6355\u83b7\u5230\u4e0d\u786e\u5b9a\u6027\u3002         \u5178\u578b\u7684\u8bed\u4e49\u6982\u5ff5\uff0c\u6bd4\u5982\u623f\u95f4\u3001\u8d70\u5eca\u3001\u7a7a\u95f4\u5173\u7cfb\uff08\u90bb\u63a5\u3001\u8fde\u901a\uff09\u3001\u5176\u4ed6\u5c5e\u6027\uff08\u5982\u77e9\u5f62\uff09\u3002\u8fd9\u4e9b\u8bed\u4e49\u4fe1\u606f\u6709\u52a9\u4e8e\u6784\u5efa\u5730\u56fe\u3002\u867d\u7136\u8bed\u4e49\u673a\u5668\u4eba\u5236\u56fe\u6ca1\u6709\u50cf\u77e2\u91cf\u6216\u62d3\u6251\u5236\u56fe\u4e00\u6837\u5f97\u5230\u5e7f\u6cdb\u7814\u7a76\uff0c\u4f46\u4e5f\u6709\u4e00\u4e9b\u91cd\u8981\u7684\u8d21\u732e\u3002 \u6587\u732e\u301011\u3011\u4e2d\u7684\u65b9\u6cd5\u4f5c\u4e3a\u8bb8\u591a\u79cd\u8bed\u4e49\u5236\u56fe\u65b9\u6cd5\u7684\u5148\u9a71\uff0c\u7ed3\u5408\u4e86\u7f51\u683c\u548c\u62d3\u6251\u5236\u56fe\u65b9\u6cd5\u80fd\u591f\u540c\u65f6\u83b7\u5f97\u9ad8\u7cbe\u5ea6\u3001\u4e00\u81f4\u6027\u7684\u77e2\u91cf\u56fe\u548c\u6709\u6548\u62d3\u6251\u56fe\u3002 Wolf and Sukhatme [14] \u63d0\u51fa\u4e86\u4f7f\u7528\u9690\u9a6c\u5c14\u53ef\u592b\u6a21\u578b\u548c\u652f\u6301\u5411\u91cf\u673a\u6765\u89e3\u51b3\u5730\u5f62\u5236\u56fe\u548c\u57fa\u4e8e\u6d3b\u52a8\u5236\u56fe\u4e2d\u6240\u5b58\u5728\u7684\u95ee\u9898\u3002\u6587\u732e [10], [2] \u548c [3]\u5229\u7528\u8bed\u4e49\u6807\u7b7e\u6765\u6807\u6ce8\u4f4d\u7f6e\u548c\u533a\u57df\u3002 Douillard\u7b49\u4eba\u63d0\u51fa\u4f7f\u7528\u6761\u4ef6\u968f\u673a\u573a\uff08conditional random fields\uff09\u6784\u5efa\u5ba4\u5916\u73af\u5883\u5bf9\u8c61\u5730\u56fe\u3002\u6b64\u5916\uff0c\u4e00\u4e9b\u5b66\u8005\u8fd8\u63d0\u51fa\u4e86\u5229\u7528\u8bed\u4e49\u6807\u6ce8\u73af\u5883\u7ed3\u6784\u7684\u65b9\u6cd5\uff0c\u6bd4\u5982\u5ba4\u5916\u73af\u5883\u7684\u9053\u8def\uff08traversable terrain\uff09\u3001\u5ba4\u5185\u73af\u5883\u4e2d\u7684\u5899\u3001\u5929\u82b1\u677f\u548c\u95e8\u3002\u6bd4\u8f83\u5178\u578b\u7684\u4f8b\u5b50\u5982[8], [12], [6] \u548c[9]\u3002          In recent years, techniques for building metric maps of indoor environments have been intensely studied, and they perform very well in noumerous applications. Simultaneous Localization and […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9],"tags":[63,62,64],"_links":{"self":[{"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=\/wp\/v2\/posts\/181"}],"collection":[{"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=181"}],"version-history":[{"count":2,"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=\/wp\/v2\/posts\/181\/revisions"}],"predecessor-version":[{"id":183,"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=\/wp\/v2\/posts\/181\/revisions\/183"}],"wp:attachment":[{"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=181"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=181"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/braininspirednavigation.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=181"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}