Collision avoidance

About: Collision avoidance is a research topic. Over the lifetime, 8014 publications have been published within this topic receiving 111414 citations.

Continuous 3D sensing for navigation and SLAM in cluttered and dynamic environments

Abstract: Navigation and mapping is well understood for dynamic 2D or static 3D environments since elaborated approaches exist that address the problems faced in standard mobile robot applications However, todaypsilas challenge lies in combining the strengths of these approaches to obtain a system capable of performing safe navigation and obstacle avoidance based on rich 3D information of the environment while still being capable of reacting to sudden dynamic changes In this paper we will present a methodology for continuously sensing environments in 3D and the necessary representations for exploiting the so gathered data in a way efficient enough to perform real-time 3D data based obstacle avoidance and online SLAM

Distributed Computational Guidance for High-Density Urban Air Mobility with Cooperative and Non-Cooperative Collision Avoidance

Abstract: Urban Air Mobility (UAM) will result in numerous aircraft which will need to respond to a dynamically changing airspace to safely reach their destinations. We use a highly efficient Markov Decision Process (MDP) based trajectory planner to demonstrate multi-agent distributed trajectory planning that can safely avoid cooperative and non-cooperative actors in the high-density free flight airspace. We demonstrate the algorithm in an urban setting where multiple aircraft all navigate to their designated landing site while avoiding cooperative and non-cooperative aircraft. We study the algorithm performance as the aircraft density increases to demonstrate scalability and the effect of cooperative versus non-cooperative actors in the environment.

On Automatic Collision Avoidance Systems

Abstract: In future automotive collision avoidance systems (CAS) collision-free path planning will be required. For this reason, two possible path planning techniques are compared. The first method is based on the mathematical theory of differential games, the second method focuses on so-called elastic bands. However, the method of elastic bands is essentially modified to provide solutions in complex driving situations. Furthermore, it is shown how path planning, path following control and driving condition estimation can be embedded in a possible overall CAS-setup. Therein, driving conditions are estimated based on the characteristic velocity. Finally, simulation results for an emergency maneuver are presented.

Collision avoidance for two robots sharing a common workspace

Abstract: Two second hand robots and an old PC were used to demonstrate co-operative working in the same space. The overall performance of the system, though slow, was considerably greater than could have been achieved without the synergy of all three control elements, obtained through simple serial communications.

The Autosea project: Developing closed-loop target tracking and collision avoidance systems

Abstract: Autonomous surface vehicles and maritime autonomous surface ships must rely on sense-and-avoid systems for navigating safely among other ships. The main objective of this paper is to present examples of such systems, and their verification in full-scale collision avoidance experiments as part of the research project "Sensor fusion and collision avoidance for autonomous surface vehicles" (Autosea). Lessons learned from the progression of experiments have led to increasing robustness of the methods, and provide a foundation for several important topics of further research in the near future.