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
TL;DR: In this paper, a regression-based approach is proposed to detect flying objects such as UAVs and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves.
Abstract: We propose an approach to detect flying objects such as UAVs and aircrafts when they occupy a small portion of the field of view, possibly moving against complex backgrounds, and are filmed by a camera that itself moves.
Solving such a difficult problem requires combining both appearance and motion cues. To this end we propose a regression-based approach to motion stabilization of local image patches that allows us to achieve effective classification on spatio-temporal image cubes and outperform state-of-the-art techniques.
As the problem is relatively new, we collected two challenging datasets for UAVs and Aircrafts, which can be used as benchmarks for flying objects detection and vision-guided collision avoidance.
32 citations
15 Apr 2008
TL;DR: An efficient vehicle collision avoidance strategy for intelligent transport systems that first clusters vehicles according to the features of their movement and a risk-aware MAC protocol is designed to enhance the responsiveness of the proposed CCA system.
Abstract: In this paper, we develop an efficient vehicle collision avoidance strategy for intelligent transport systems. The proposed strategy first clusters vehicles according to the features of their movement (e.g., direction of movement, inter-vehicle distance, and relative velocity). To enhance the responsiveness of the proposed CCA system, a risk-aware MAC protocol is designed. In the proposed scheme, an emergency level is defined for each vehicle based on its order in its respective cluster. The emergency level reflects the risk of a vehicle to meet an emergency situation in the platoon. The medium access delay of each vehicle is set as a function of its emergency level in a way that enables vehicles in emergency situations to promptly disseminate warning messages to neighboring vehicles and to accordingly minimize chain collisions. The proposed CCA system is dubbed cluster- based risk-aware CCA (C-RACCA). The performance of the proposed C-RACCA system is evaluated via simulations and encouraging results are obtained.
32 citations
TL;DR: A five-layer hierarchy to integrate models, data, and tools is proposed for benefits assessment and requirements development for crash avoidance systems, and its use is illustrated by analysis of a forward collision warning system.
Abstract: A five-layer hierarchy to integrate models, data, and tools is proposed for benefits assessment and requirements development for crash avoidance systems. The framework is known as HARTCAS: Hierarchical Assessment and Requirements Tools for Crash Avoidance Systems. The analysis problem is multifaceted and large-scale. The driving environment is diverse and uncertain, driver behavior and performance are not uniform, and the range of applicable collision avoidance technologies is wide. Considerable real-world data are becoming available on certain aspects of this environment, although the collection of experimental data on other aspects is constrained by technological and institutional issues. Therefore, analyses of collision avoidance systems are to be conducted by collecting data on nominal operating conditions to the greatest extent possible and by using such data to build models for analysis of the rare, abnormal conditions. HARTCAS provides a framework within which to structure the collection and use of...
32 citations
30 Dec 2008
TL;DR: Simulation results show that the proposed prediction method for vehicle-to-pedestrian collision avoidance works well in a complex structured environment and the prediction is consistent with actual behaviors.
Abstract: This paper proposes a prediction method for vehicle-to-pedestrian collision avoidance, which learns and then predicts pedestrian behaviors as their motion instances are being observed. During learning, known trajectories are clustered to form motion patterns (MP), which become knowledge a priori to a multi-level prediction model that predicts long-term or short-term pedestrian behaviors. Simulation results show that it works well in a complex structured environment and the prediction is consistent with actual behaviors.
32 citations
TL;DR: This paper uses virtual impedance control for reactive, smooth, and consistent collision avoidance that interferes minimally with the original task and provides a proof of convergence if the original controller is stable with and without projection.
Abstract: Collision avoidance is essential for safe robot manipulation. Especially with humans around, robots should work only when safety can be robustly guaranteed. In this paper, we propose using virtual impedance control for reactive, smooth, and consistent collision avoidance that interferes minimally with the original task. The virtual impedance control operates in the risk space, a vector space describing the possibilities of all forthcoming collisions, and is designed to elude all risks in a consistent response in order to create assuring human-robot interaction experiences. The proposed scheme intrinsically handles kinematic singularity and the activation of avoidance using a boundary layer defined on the spectrum of Jacobian. In cooperation with the original controller, the proposed avoidance scheme provides a proof of convergence if the original controller is stable with and without projection. In simulations and experiments, we verified the characteristics of the proposed control scheme and integrated the system with Microsoft Kinect to monitor the workspace for real-time collision detection and avoidance. The results show that the proposed approach is suitable for robot operation with humans nearby.
32 citations