Topic
Collision avoidance system
About: Collision avoidance system is a research topic. Over the lifetime, 1788 publications have been published within this topic receiving 23667 citations.
Papers published on a yearly basis
Papers
More filters
Posted Content•
TL;DR: This paper proposes an approach whereby a parameterized resolution logic that is considered trusted for a given range of its parameters is adaptively tuned online and presented a dynamic programming approach for adapting the parameters dynamically based on the encounter state.
Abstract: Safely integrating unmanned aerial vehicles into civil airspace is contingent upon development of a trustworthy collision avoidance system. This paper proposes an approach whereby a parameterized resolution logic that is considered trusted for a given range of its parameters is adaptively tuned online. Specifically, to address the potential conservatism of the resolution logic with static parameters, we present a dynamic programming approach for adapting the parameters dynamically based on the encounter state. We compute the adaptation policy offline using a simulation-based approximate dynamic programming method that accommodates the high dimensionality of the problem. Numerical experiments show that this approach improves safety and operational performance compared to the baseline resolution logic, while retaining trustworthiness.
12 citations
01 Aug 2020
TL;DR: The method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents, and shows that the proposed algorithm generates test suits composed mostly of challenging scenarios.
Abstract: We propose a method for scenario-based testing of maritime collision avoidance systems. The goal is to test an autonomous agent in scenarios that can lead to an unacceptable risk of collision or may clearly not comply with the International Regulations for Preventing Collisions at Sea (COLREGs).Our method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents. Our experimental results show that the proposed algorithm generates test suits composed mostly of challenging scenarios. This allows us to validate quickly if the agent under test can perform the collision avoidance maneuvers safely while abiding the COLREGs.
12 citations
Patent•
16 Jan 2017
TL;DR: In this paper, a vehicular collision avoidance system includes a first image processor that processes image data captured by a forward-viewing camera to detect vehicles and determine vehicles present in the occupied lane and adjacent lane.
Abstract: A vehicular collision avoidance system includes a first image processor that processes image data captured by a forward-viewing camera to detect vehicles and determine vehicles present in the occupied lane and adjacent lane, and a second image processor that processes image data captured by a rearward-viewing camera to detect the presence of vehicles and determine vehicles present in the occupied lane and adjacent lane. Information relating to the vehicles is wirelessly transmitted between the vehicles. Responsive at least in part to at least one of (i) image processing of image data captured by the forward-viewing camera and/or rearward-viewing camera, (ii) sensor data sensed by at least one other sensor, and (iii) information transmitted to or from the equipped vehicle via the car2car (v2v) communication system, the collision avoidance system is operable to determine imminence of collision with the equipped vehicle by another vehicle present exterior the equipped vehicle.
11 citations
Patent•
10 Dec 2003
TL;DR: A collision avoidance system for three or more vessels including a path predicting engine to predict the future position of each vessel, a conflict detection engine to determine whether any vessels are in conflict based on the predicted path determined by the path predictor, and a conflict resolution engine to decide a course of action for any said vessels determined to be in conflict by a conflict detector as mentioned in this paper.
Abstract: A collision avoidance system for three or more vessels including a path predicting engine to predict the future position of each said vessel; a conflict detection engine to determine whether any said vessels are in conflict based on the predicted path determined by said path predicting engine; and a conflict resolution engine to determine a course of action for any said vessels determined to be in conflict by said conflict detection engine.
11 citations
Patent•
08 Jan 2014
TL;DR: In this article, an intelligent decision module is used to decide, on the basis of the time required for the electric vehicle to reach the vehicle or obstacle in front of same, whether to continue to proceed normally or to activate a regenerative braking mode or a composite braking mode involving simultaneous activation of the regenerative and mechanical braking modes.
Abstract: An electric vehicle collision avoidance system and automatic braking method comprising: an information collection module (101), used to collect, in real time, information regarding the distance between the electric vehicle and the vehicle or obstacle in front of same, and also current driving speed; an information processing module (102), used to calculate, in real time, the time required for the electric vehicle to reach the vehicle or obstacle in front of same as well as the regenerative braking safety time and mechanical braking safety time; an intelligent decision module (103), used to decide, on the basis of the time required for the electric vehicle to reach the vehicle or obstacle in front of same and also both the regenerative braking safety time and the mechanical braking safety time, whether to continue to proceed normally or to activate a regenerative braking mode or a composite braking mode involving simultaneous activation of the regenerative braking and mechanical braking modes; a regenerative braking module (104), which activates regenerative braking for the electric vehicle according to regenerative braking mode activation signals provided by the intelligent decision module; a mechanical braking module (105), which activates mechanical braking for the electric vehicle according to composite braking mode activation signals provided by the intelligent decision module.
11 citations