Topic
Collision avoidance
About: Collision avoidance is a research topic. Over the lifetime, 8014 publications have been published within this topic receiving 111414 citations.
Papers published on a yearly basis
Papers
More filters
22 Feb 2009
TL;DR: The strategy of combining the improved artificial potential field method and the rules based on priority is used to study the collision avoidance planning problem in multi-robot systems and can make robot to find a collision-free path from a starting point to the goal quickly in an environment with many obstacles.
Abstract: For the real-time and distributed features of multi-robot system, the strategy of combining the improved artificial potential field method and the rules based on priority is used to study the collision avoidance planning problem in multi-robot systems The traditional artificial potential field method has some drawbacks, improved artificial potential field based on simulated annealing algorithm satisfactorily resolved this issue, so robots can found a local collision-free path in the complex environment Through the robot's movement vector trail, collisions between robots can be detected, thereby activate the collision avoidance rules Coordination between the robots by the priority based rules improves the real-time property of multi-robot system well The combination of these two methods can make robot to find a collision-free path from a starting point to the goal quickly in an environment with many obstacles Finally, the VC-based simulation environment tests the feasibility of the method
32 citations
07 Sep 1997
TL;DR: It is shown that appropriate behaviors for collision avoidance can be successfully acquired through the proposed learning process through the reinforcement learning.
Abstract: We discuss adaptive behavior acquisition for collision avoidance among multiple autonomous mobile robots which are equipped with the locally communicable infrared sensory system (LOCISS). The LOCISS is a local sensing device for collision avoidance by which robots can detect other robots and obstacles and discriminate them by exchanging relevant information. We (1996) reported previously a collision avoidance method between two robots based on the predetermined rules using LOCISS. It is, however, difficult to realize collision avoidance among three or more robots by the predetermined rules only because situations around the robots become more complicated as the number of robots increases. Thus, it is desirable for the robots to have an adaptive capability for acquisition of the behaviors to avoid collision with other robots and obstacles. To acquire the adaptive behavior, the reinforcement learning is introduced in this paper. It is shown that appropriate behaviors for collision avoidance can be successfully acquired through the proposed learning process.
32 citations
04 Dec 2009
TL;DR: In this paper, an approach to detect and resolution of air traffic conflicts in a 3D airspace between two aircraft is presented, based on the current 3D position and speed vector of both aircraft and a cylindrical minimum safety protection zone (PZ).
Abstract: As the aviation community moves toward the Next Generation Air Transportation System (NextGen), the current Traffic Alert and Collision Avoidance System (TCAS II) may become inadequate. This paper presents a novel approach to detection and resolution of air traffic conflicts in a 3-dimensional (3-D) airspace between two aircraft. The inputs to the detection algorithm are the current 3-D position and speed vector of both aircraft and a cylindrical minimum safety protection zone (PZ). For collision avoidance systems (CASs), the size of the configurable PZ can be assigned values that the Federal Aviation Administration (FAA) considers as a near mid air collision (NMAC1) incident. When available, additional inputs, such as measurement uncertainties and intruder type (e.g., manned/unmanned), can be used to alter the default protection zone. The conflict detection takes into account the 3-D encounter (e.g., closure rate, miss distance, relative converging maneuver). The resolution algorithm initially computes a set of six resolution advisories (RAs) and associated resolution alert times that ensure no violation of the protection zone. Two solutions are computed for each of the three dimensions: ground track, ground speed, and vertical speed. The initial resolution advisories (RAs) solutions take into account ownship capability (i.e., max climb/descent rate, max turn rate, max speed/stall speed) and ownship pilot response delay (e.g., autonomous vs. manual RA execution). These six solutions are subsequently down-selected in two steps: first, based on the encounter geometry, a single implicitly2 coordinated, independent solution is selected for each of the three dimensions; then, based on ownship preferences and operational considerations a final RA solution is computed.
31 citations
TL;DR: An algorithm for performing collision avoidance with robotic manipulators that does not require any a priori knowledge of the motion of other objects in its environment and is computationally efficient enough to be implemented in real time.
Abstract: Purpose – The purpose of this paper is to present an algorithm for performing collision avoidance with robotic manipulators.Design/methodology/approach – The method does not require any a priori knowledge of the motion of other objects in its environment. Moreover, it is computationally efficient enough to be implemented in real time. This is achieved by constructing limitations on the motion of a manipulator in terms of its allowable instantaneous velocity. Potential collisions and joint limits are formulated as linear inequality constraints. Selection of the optimal velocity is formulated as a convex optimization and is solved using an interior point method.Findings – Experimental results with two industrial arms verify the effectiveness of the method and illustrate its ability to easily handle many simultaneous potential collisions.Originality/value – The resulting algorithm allows arbitrary motions commanded to the robot to be modified on‐line in order to guarantee optimal real‐time collision avoidanc...
31 citations
Posted Content•
TL;DR: An on-board vision-based approach for avoidance of moving obstacles in dynamic environments based on an efficient obstacle detection and tracking algorithm based on depth image pairs, which provides the estimated position, velocity and size of the obstacles.
Abstract: In this paper, we present an on-board vision-based approach for avoidance of moving obstacles in dynamic environments. Our approach relies on an efficient obstacle detection and tracking algorithm based on depth image pairs, which provides the estimated position, velocity and size of the obstacles. Robust collision avoidance is achieved by formulating a chance-constrained model predictive controller (CC-MPC) to ensure that the collision probability between the micro aerial vehicle (MAV) and each moving obstacle is below a specified threshold. The method takes into account MAV dynamics, state estimation and obstacle sensing uncertainties. The proposed approach is implemented on a quadrotor equipped with a stereo camera and is tested in a variety of environments, showing effective on-line collision avoidance of moving obstacles.
31 citations