Visual sonar: fast obstacle avoidance using monocular vision

Lenser, Scott; Veloso, Manuela

doi:10.1109/iros.2003.1250741

Cited by 97 publications

(57 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…P1 is any point, and P2 is the projection point of P1. Point P2 on picture plane is the intersection point of picture plane and OC (Optical Center)-P1 line [6]. Camera images are converted into digital image and stored in (u,v) form which is in the Cartesian coordinate system.…”

Section: Distance Calculation Based On Monocular Visionmentioning

confidence: 99%

Anti-Collision Warning Algorithm based on Visual Perception in Front of Vehicle

Ding¹,

Zhang²,

Zhou³

et al. 2017

Proceedings of the 2017 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2017)

View full text Add to dashboard Cite

Abstract. The vehicles' driving safety plays an important role in the transportation safety's development, and it's a necessary requirement in intelligent transportation and intelligent vehicle. The point that is suggested in this paper is that vehicles' collision warning system which is based on computer vision, and the system is built on computer vision, pattern recognition, machine learning and some other artificial intelligent theory and techniques, discerning the vehicles which is in front of your vehicle and measure the security range, warning the possible danger timely to make sure your drive safe. We use the characteristic which is called haar of the samples to train in the classifier to get a cascaded classifier named Boosted, loading the classifier and image of the vehicles marked and calculating the distance and relative speed. In the last, we do a lot of system simulation experiments, verifying the accuracy and the effectiveness of the system from vehicle outline detection results and safe vehicle determination.

show abstract

Section: Distance Calculation Based On Monocular Visionmentioning

confidence: 99%

Anti-Collision Warning Algorithm based on Visual Perception in Front of Vehicle

Ding¹,

Zhang²,

Zhou³

et al. 2017

Proceedings of the 2017 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2017)

View full text Add to dashboard Cite

show abstract

“…The robots are also white and gray, and they wear pink or blue waist bands as uniforms so any non-green thing lying on the field is an obstacle, except for the field lines which are white. We utilize a simplified version of the Visual Sonar algorithm by Lenser and Veloso [10] and the algorithm by Hoffmann et al [11]. We scan the image along evenly spaced vertical lines starting from the bottom end and continue until we see a certain number of non-green pixels.…”

Section: A Free Space Detectionmentioning

confidence: 99%

Complementary humanoid behavior shaping using corrective demonstration

Meriçli

Veloso

Akın

2010

2010 10th IEEE-RAS International Conference on Humanoid Robots

View full text Add to dashboard Cite

Abstract-A humanoid robot can perform a task through a policy mapping from its sensed state to the appropriate task actions. We assume that a hand-coded controller can capture such a mapping only for the basic cases of the given task. As the complexity of the situation increases, the harder it becomes to refine the controller, and such refinements are often tedious and error prone. Based on the fact that a human can detect the failures of a robot executing the hand-coded controller, in this paper we present a corrective learning from demonstration approach to improve the robot performance. Corrections are captured as new state action pairs, and during the autonomous humanoid robot execution, the controller is replaced by the demonstration corrections when the new state is found to be similar to the corrected state. We focus on the Aldebaran Nao humanoid robot and a concrete complex ball dribbling task in an environment with obstacles. We present experimental results showing an improvement in the humanoid task performance when the corrective demonstration is used in addition to the basic hand-coded controller.

show abstract

“…In fact, we use the raw range scans, and this paper shows that a robust localization is achievable. Lenser and Veloso have developed a system which mimics the working of a sonar sensor using a monocular camera that detects obstacles (as color transitions) along previously determined lines in the image [14]. However, although the basic idea is similar, our aim is much broader: we want to mimic the working of a laser rangefinder with an omnidirectional camera [therefore, with a 360 field of view (FOV)] in order to be able, not only to avoid the obstacles as Lenser, but also to localize the robot with a Monte Carlo localization software almost unaltered from the one proposed by Thrun et al [24], in which they used laser rangefinders.…”

Section: Related Workmentioning

confidence: 99%

Omnidirectional vision scan matching for robot localization in dynamic environments

et al. 2006

View full text Add to dashboard Cite

Abstract-The localization problem for an autonomous robot moving in a known environment is a well-studied problem which has seen many elegant solutions. Robot localization in a dynamic environment populated by several moving obstacles, however, is still a challenge for research. In this paper, we use an omnidirectional camera mounted on a mobile robot to perform a sort of scan matching. The omnidirectional vision system finds the distances of the closest color transitions in the environment, mimicking the way laser rangefinders detect the closest obstacles. The similarity of our sensor with classical rangefinders allows the use of practically unmodified Monte Carlo algorithms, with the additional advantage of being able to easily detect occlusions caused by moving obstacles. The proposed system was initially implemented in the RoboCup Middle-Size domain, but the experiments we present in this paper prove it to be valid in a general indoor environment with natural color transitions. We present localization experiments both in the RoboCup environment and in an unmodified office environment. In addition, we assessed the robustness of the system to sensor occlusions caused by other moving robots. The localization system runs in real-time on low-cost hardware.

show abstract

Visual sonar: fast obstacle avoidance using monocular vision

Cited by 97 publications

References 9 publications

Anti-Collision Warning Algorithm based on Visual Perception in Front of Vehicle

Anti-Collision Warning Algorithm based on Visual Perception in Front of Vehicle

Complementary humanoid behavior shaping using corrective demonstration

Omnidirectional vision scan matching for robot localization in dynamic environments

Contact Info

Product

Resources

About