An evaluation version of the article can be accessed here (PDF)<\/a><\/p>\n
ABSTRACT:
This paper focuses on real-world implementation and veri\ufb01cation of a local, model-based stochastic automatic collision avoidance algorithm, with application in remotely-piloted (tele-operated) unmanned aerial vehicles(UAVs). Automatic collision detection and avoidance for tele-operated UAVs can reduce the workload of pilots to allow them to focus on the task at hand, such as searching for victims in a search and rescue scenario following a natural disaster. The proposed algorithm takes the pilot\u2019s input and exploits the robot\u2019s dynamics to predict the robot\u2019s trajectory for determining whether a collision will occur.Using on-board sensors for obstacle detection, if a collision is imminent, the algorithm modi\ufb01es the pilot\u2019s input to avoid the collision while attempting to maintain the pilot\u2019s intent.The algorithm is implemented using a low-cost on-board computer, \ufb02ight-control system, and a two-dimensional laser illuminated detection and ranging sensor for obstacle detection along the trajectory of the robot. The sensor data is processed using a split-and-merge segmentation algorithm and an approximate Minkowski difference. Results from \ufb02ight tests demonstrate the algorithm\u2019s capabilities for tele-operated collision-free control of an experimental UAV.<\/p>\n
![](\"http:\/\/www.kam.k.leang.com\/academics\/wp-content\/uploads\/2017\/02\/CollisionAvoidanceConceptUpdated03.jpg\")
Collision avoidance for tele-operated UAVs: A UAV pilot controls the aerial vehicle and provides input u. When a collision is detected with on-board sensing and state estimation, the algorithm produces an input d\u0001u that augments the pilot’s input u to steer the robot away from the obstacle. The control block diagram includes the sensing block and the collision avoidance block where the pilot’s input u is passed through the dynamics model to obtain the estimated trajectory ^p along with uncertainty in the motion model m. This trajectory is checked for collisions against the obstacles O. If a collision is detected, the algorithm calculates a change in input d\u0001u to avoid collisions. If the input u + \u0001du is deemed safe, it is then passed to the robot.<\/p><\/div>\n
\u00a0<\/p>\n
![\"\"](\"http:\/\/www.kam.k.leang.com\/academics\/wp-content\/uploads\/2017\/02\/HallwayExp03.jpg\")
Experimental results showing aerial robot flying through an “S”-shaped hallway.<\/p><\/div>\n
\u00a0<\/p>\n\n\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
Journal article entitled, “On-board model-based automatic collision avoidance: application in remotely-piloted unmanned aerial vehicles”, by D. Bareiss, J. R. Bourne and K. K. Leang was recently published in Autonomous Robots. The article can be accessed by following this link: http:\/\/rdcu.be\/oOIGAn evaluation version of the article can be […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"footnotes":""},"categories":[73,76],"tags":[],"class_list":["post-2119","post","type-post","status-publish","format-standard","hentry","category-all_news","category-pubs"],"_links":{"self":[{"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/posts\/2119","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/comments?post=2119"}],"version-history":[{"count":8,"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/posts\/2119\/revisions"}],"predecessor-version":[{"id":2837,"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/posts\/2119\/revisions\/2837"}],"wp:attachment":[{"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/media?parent=2119"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/categories?post=2119"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.kam.k.leang.com\/academics\/wp-json\/wp\/v2\/tags?post=2119"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}