Topic
Obstacle
About: Obstacle is a research topic. Over the lifetime, 9517 publications have been published within this topic receiving 94760 citations. The topic is also known as: impediment & barrier.
Papers published on a yearly basis
Papers
More filters
•
27 Jun 1996
TL;DR: In this article, an electronic obstacle detection system for guiding and warning a motorist of obstacles in the detection area while backing up is presented, which includes a pair of sensor clusters (14 and 16) to be affixed to the rear of the vehicle and an audio-visual indicator located in the vehicle.
Abstract: An electronic obstacle detection system (12) for guiding and warning a motorist of obstacles in the detection area while backing up. The main components of the system include a pair of sensor clusters (14 and 16) to be affixed to the rear of the vehicle (10), a pair of exterior visual indicators (18 and 20), and an audio-visual indicator (22) located in the vehicle (10). Each of the sensor clusters (14 and 16) are encased in a housing (30) having angled, stepped portions (44, 46 and 48) configured to provide complete area coverage of transmitted and received signals.
165 citations
••
06 Jan 1988TL;DR: In the case where the final positions of the obstacles are specified the general problem is shown to be PSPACE-hard and an algorithm is given when there is one movable obstacle with the same preprocessing time as the previous algorithm but with a different query time.
Abstract: Motion planning algorithms have generally dealt with motion in a static environment, or more recently, with motion in an environment that changes in a known manner. We consider the problem of finding collision-free motions in a changeable environment. That is, we wish to find a motion for an object where the object is permitted to move some of the obstacles. In such an environment the final positions of the movable obstacles may or may not be part of the goal. In the case where the final positions of the obstacles are unspecified, the motion planning problem is shown to be NP-hard. An algorithm that runs in O(n2logn) time after O(n3log2n) preprocessing time is presented when the object to be moved is polygonal and there is only one movable polygonal obstacle in a polygonal environment of complexity O(n). In the case where the final positions of the obstacles are specified the general problem is shown to be PSPACE-hard and an algorithm is given when there is one movable obstacle with the same preprocessing time as the previous algorithm but with O(n2) query time.
165 citations
•
19 Oct 1993TL;DR: In this paper, an obstacle sensing apparatus for vehicles which enables efficient obstacle sensing and improves sensing precision is presented. But the apparatus comprises a section for predicting a deduced traveling passage on which the vehicle will travel, based on a steering angle, a yaw rate and a velocity of the vehicle, a section having a CCD camera, for detecting a current traveling-passage, a scanning-type radar unit for sensing obstacles within a predetermined area, and a danger level judging section for judging danger levels of the sensed obstacles.
Abstract: An obstacle sensing apparatus for vehicles which enables efficient obstacle sensing and improves sensing precision. The apparatus comprises a section for predicting a deduced traveling-passage on which the vehicle will travel, based on a steering angle, a yaw rate and a velocity of the vehicle, a section having a CCD camera, for detecting a current traveling-passage on which the vehicle is currently moving, a scanning-type radar unit for sensing obstacles within a predetermined area, and a danger level judging section for judging danger levels of the sensed obstacles, based on the deduced traveling-passage and the current traveling-passage. The danger level judging section sets the danger level of the obstacle sensed within an area, where the deduced traveling-passage and the current traveling-passage overlap with each other, to the highest danger level; the obstacle sensed in an area within the current traveling-passage and without the deduced traveling-passage, to an intermediate danger level; the obstacle sensed in an area within the deduced traveling-passage and without the current traveling-passage, to a lower danger level; and the obstacle sensed in an area without the current and deduced traveling-passages, to the lowest danger level.
164 citations
••
01 Jan 2015TL;DR: This paper addresses the task of detecting the closest obstacle in each direction from a driving vehicle using a single color camera and shows that the monocularbased approach outperforms existing camera-based methods including ones using stereo.
Abstract: General obstacle detection is a key enabler for obstacle avoidance in mobile robotics and autonomous driving. In this paper we address the task of detecting the closest obstacle in each direction from a driving vehicle. As opposed to existing methods based on 3D sensing we use a single color camera. The main novelty in our approach is the reduction of the task to a column-wise regression problem. The regression is then solved using a deep convolutional neural network (CNN). In addition, we introduce a new loss function based on a semi-discrete representation of the obstacle position probability to train the network. The network is trained using ground truth automatically generated from a laser-scanner point cloud. Using the KITTI dataset, we show that the our monocularbased approach outperforms existing camera-based methods including ones using stereo. We also apply the network on the related task of road segmentation achieving among the best results on the KITTI road segmentation challenge.
163 citations
••
TL;DR: The proposed algorithm brings a new solution to the problem and has several advantages compared to previous methods and is very promising for application in mobile and industrial robotics where obstacle avoidance is a feature of the robotic system.
162 citations