{"id":1753,"date":"2015-03-21T06:19:17","date_gmt":"2015-03-21T06:19:17","guid":{"rendered":"http:\/\/www.kam.k.leang.com\/academics\/?page_id=1753"},"modified":"2024-09-12T19:20:06","modified_gmt":"2024-09-12T19:20:06","slug":"feedback_pubs","status":"publish","type":"page","link":"http:\/\/www.kam.k.leang.com\/academics\/publications\/feedback_pubs\/","title":{"rendered":"Feedback control related work"},"content":{"rendered":"
<\/a><\/form>

2026<\/h3>
58.<\/div>
\"<\/div>

J. M. Anderson; K. K. Leang<\/p>

Information-based Supervised Learning of In-proximity Effects for 3D Distance Estimation and Collision Avoidance<\/a> Journal Article<\/span> <\/p>

In: <\/span>IEEE Robotics and Automation Letters, <\/span>vol. 11, <\/span>iss. 5, <\/span>pp. 5398-5405, <\/span>2026<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@article{AndersonJM_2026_RAL,
\r\ntitle = { Information-based Supervised Learning of In-proximity Effects for 3D Distance Estimation and Collision Avoidance},
\r\nauthor = {J. M. Anderson and K. K. Leang},
\r\nurl = {http:\/\/www.kam.k.leang.com\/academics\/pubs\/AndersonJM_2026_RAL.pdf},
\r\ndoi = {10.1109\/LRA.2026.3665068},
\r\nyear  = {2026},
\r\ndate = {2026-02-16},
\r\nurldate = {2026-02-16},
\r\njournal = {IEEE Robotics and Automation Letters},
\r\nvolume = {11},
\r\nissue = {5},
\r\npages = {5398-5405},
\r\nabstract = {In-proximity effects (IPE) in 3D, specifically in-ground, in-ceiling, and in-wall effects, experienced by a rotary-wing aerial robot when it flies near obstacles are leveraged for obstacle distance estimation and collision-free motion control. The proposed concept of processing onboard motor commands and inertial measurement unit (IMU) signals enables the robot to essentially ``feel'' the presence of nearby obstacles through aerodynamic interactions. The physics of IPE, along with Shannon information, are used to tailor the input space and train a deep neural network (DNN) to estimate the distance to ground, ceiling, and wall features. Simulation and physical experimental results demonstrate reliable and robust obstacle detection and collision avoidance with a median distance estimation accuracy of 93.35%, 89.22%, and 90.67% for ground, ceiling, and wall, respectively. This new form of ``sensing'' is advantageous in environments where traditional proximity sensors and vision-based obstacle detection systems may not be reliable, such as in foggy, smokey, or dusty environments where  perception is limited.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {article}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
In-proximity effects (IPE) in 3D, specifically in-ground, in-ceiling, and in-wall effects, experienced by a rotary-wing aerial robot when it flies near obstacles are leveraged for obstacle distance estimation and collision-free motion control. The proposed concept of processing onboard motor commands and inertial measurement unit (IMU) signals enables the robot to essentially ``feel'' the presence of nearby obstacles through aerodynamic interactions. The physics of IPE, along with Shannon information, are used to tailor the input space and train a deep neural network (DNN) to estimate the distance to ground, ceiling, and wall features. Simulation and physical experimental results demonstrate reliable and robust obstacle detection and collision avoidance with a median distance estimation accuracy of 93.35%, 89.22%, and 90.67% for ground, ceiling, and wall, respectively. This new form of ``sensing'' is advantageous in environments where traditional proximity sensors and vision-based obstacle detection systems may not be reliable, such as in foggy, smokey, or dusty environments where  perception is limited.<\/div>
Close<\/a><\/p><\/div>