scispace - formally typeset
Search or ask a question
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
More filters
Journal ArticleDOI
01 Sep 2020
TL;DR: This article aims to plan precise and optimal trajectory for a car-like tractor that tows standard or general N-trailers in an environment with static obstacles to address the non-convex collision avoidance constraints and the unstable kinematics.
Abstract: Trajectory planning for a tractor-trailer vehicle is challenging due to the non-convex collision avoidance constraints and the unstable kinematics. This article aims to plan precise and optimal trajectory for a car-like tractor that tows standard or general N-trailers in an environment with static obstacles. This trajectory planning scheme can be formulated as a unified optimal control problem, but numerically solving that problem is difficult. Two efforts are made to address the difficulty. First, an extended hybrid A* search algorithm is proposed to provide an initial guess for the numerical optimization. Second, the numerical optimization process is eased through adopting a progressively constrained optimization strategy, which is about sequentially handling the kinematics, collision avoidance constraints, and boundary conditions. Particularly in dealing with the collision avoidance constraints, an adaptively homotopic warm-starting algorithm is proposed, which defines a sequence of subproblems with the obstacle areas adaptively increase towards their nominal scales. Through solving these subproblems in a sequence, the whole collision avoidance difficulties are dispersed and gradually tackled. Comparative simulations are conducted to validate the efficacy of the proposed trajectory planner.

47 citations

Proceedings ArticleDOI
01 Sep 2013
TL;DR: A lightweight 3D laser scanner and visual obstacle detection using wide-angle stereo cameras and a fast reactive collision avoidance approach for safe operation in the vicinity of structures like buildings or vegetation are implemented.
Abstract: Reliably perceiving obstacles and avoiding collisions is key for the fully autonomous application of micro aerial vehicles (MAVs), Limiting factors for increasing autonomy and complexity of MAVs are limited onboard sensing and limited onboard processing power. In this paper, we propose a complete system with a multimodal sensor setup for omnidirectional obstacle perception. We developed a lightweight 3D laser scanner and visual obstacle detection using wide-angle stereo cameras. Detected obstacles are aggregated in egocentric grid maps. We implemented a fast reactive collision avoidance approach for safe operation in the vicinity of structures like buildings or vegetation.

47 citations

Proceedings ArticleDOI
25 Jun 2008
TL;DR: The principle proposed in order to avoid static obstacles is to verify that the predicted vehicle trajectory does not intersect these obstacles, and to share the position and shape of the obstacles they have detected.
Abstract: This article describes the use of predictive control for the decentralized cooperative control of unmanned aerial vehicles in an unfamiliar three-dimensional environment. It is assumed that each vehicle is equipped with an autopilot and a trajectory control unit. The autopilot insures the stability of the vehicle. The setpoints of the autopilot are calculated by the trajectory control unit, thus forming a cascade control structure. The trajectory control unit relies on a predictive control algorithm to calculate the optimal commands (autopilot setpoints) such that the vehicle will reach fixed targets at known positions while avoiding static obstacles that are detected en route. The advantage in using predictive control is that it offers great flexibility in the objective function to optimize while respecting constraints such as command limits, limits on the displacement that a vehicle can carry out, and the constraints that allow obstacle avoidance. The principle proposed in order to avoid static obstacles (that are assumed ellipsoid) is to verify that the predicted vehicle trajectory does not intersect these obstacles. With the objective to increase performance, cooperation between vehicles must also be privileged. Thus, if some vehicles are within the communication range, they can share the position and shape of the obstacles they have detected. Simulations illustrate the method and higlight the benefits of cooperation.

47 citations

Proceedings ArticleDOI
18 Nov 2011
TL;DR: A reliable, real-time intersection collision avoidance system based solely on infrastructure communication is proposed, which utilizes telematics and wireless sensor networks to monitor approaching traffic, detect possible collision, and then transfer information to drivers, warning them of high collision probability.
Abstract: Nearly one third of all documented vehicle collisions are reported at urban and rural intersections, and this number continues to rise in spite of technological innovations for vehicle safety. Most collision avoidance systems currently under investigation are based on road-vehicle or inter-vehicle communication. However, reliability remains an issue, as high mobility often leads to message collisions and link breakage. In this paper reliable, real-time intersection collision avoidance (ICA) system based solely on infrastructure communication is proposed. ICA utilizes telematics and wireless sensor networks (WSN) to monitor approaching traffic, detect possible collision, and then transfer information to drivers, warning them of high collision probability.

47 citations


Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20242
2023547
20221,269
2021503
2020621
2019661