{"id":171,"date":"2019-10-24T11:49:13","date_gmt":"2019-10-24T09:49:13","guid":{"rendered":"https:\/\/project.inria.fr\/crowdscience\/?page_id=171"},"modified":"2020-03-05T17:17:30","modified_gmt":"2020-03-05T16:17:30","slug":"crowdbot","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/crowdscience\/project\/crowdbot\/","title":{"rendered":"CrowdBot"},"content":{"rendered":"

\"\"<\/a><\/p>\n

CrowdBot<\/a> is a European Union Horizon 2020 (<\/span>EU H2020<\/a>) project about <\/span>\u201cSafe Navigation of Robots in Dense Human Crowds\u201d<\/strong>. The name \u201cCrowdBot\u201d is an\u00a0amalgam of human \u201ccrowd\u201d and machine \u201cbot.\u201d In CrowdBot we aim to equip robots with tools and algorithms to navigate in crowded areas either autonomously or by using shared-control<\/span><\/p>\n

Today\u2019s robots are programmed to stop when getting too close to a human or an obstacle, in order to avoid collisions. However, this prevents robots from entering densely frequented areas and performing effectively in these high dynamic environments.<\/p>\n

CrowdBot gathers the required expertise from 7 industrial and academic partners to develop new robot capabilities:\u00a0RWTH<\/a> work on sensing abilities to estimate the crowd motion around the robot.<\/span>\u00a0At Inria<\/a> research center in Rennes, we improve cognitive abilities for the robot to predict the short term evolution of the crowd state. Our team also develop a tool of crowd simulation. A\u00a0team from ETHZ<\/a> university is developing the navigation module of the robots to perform safe motion at close range from people.\u00a0And EPFL is responsible for developing the “Reactive Navigation” so that the robot take the right decision if there is a present or imminent collision and to predict pedestrian behavior after collisions.<\/p>\n

At the same time, the other partners develop or design 4 different robotic platforms for this project:<\/p>\n