Doing the Right Thing: Collision Avoidance for Autonomous Air Vehicles

Author(s):  
Chinmay Mishra ◽  
Mitul Mehta ◽  
Elias J. Griffith ◽  
Jason F. Ralph
Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4141
Author(s):  
Wouter Houtman ◽  
Gosse Bijlenga ◽  
Elena Torta ◽  
René van de Molengraft

For robots to execute their navigation tasks both fast and safely in the presence of humans, it is necessary to make predictions about the route those humans intend to follow. Within this work, a model-based method is proposed that relates human motion behavior perceived from RGBD input to the constraints imposed by the environment by considering typical human routing alternatives. Multiple hypotheses about routing options of a human towards local semantic goal locations are created and validated, including explicit collision avoidance routes. It is demonstrated, with real-time, real-life experiments, that a coarse discretization based on the semantics of the environment suffices to make a proper distinction between a person going, for example, to the left or the right on an intersection. As such, a scalable and explainable solution is presented, which is suitable for incorporation within navigation algorithms.


2015 ◽  
Vol 63 (3) ◽  
Author(s):  
Alexander Stoff ◽  
Hermann Winner

AbstractThis paper analyzes and evaluates alternative options for action and earliest possible dates for intervention for an automated safety function to avoid or mitigate collisions in priority situations in which the right of way regulations are violated by the crossing road users. Based on a simulation of the collision avoidance strategies, the potential safety benefits could be predicted.


2012 ◽  
pp. 338-356
Author(s):  
Theodor Borangiu ◽  
Florin Daniel Anton ◽  
Silvia Anton

The chapter also discusses a new method of using robots to interact with humans (natural interaction) to provide assistance services. Using depth sensors, the robots are able to detect the human operator and to avoid collisions. Collision avoidance is implemented using a depth sensor, which monitors the activity outside and inside the multi-robot system workspace, using skeleton tracking, which allows the robot to detect collisions and stop the motion at the right time.


Author(s):  
James A. Ramsey ◽  
Ryan T. Ratliff ◽  
Kevin A. Wise ◽  
Eugene Lavretsky

Author(s):  
R. Vaidyanathan ◽  
C.A. Williams ◽  
T.S. Prince ◽  
R.E. Ritzmann ◽  
R.D. Quinn

Sign in / Sign up

Export Citation Format

Share Document