Laser intensity-based obstacle detection (original) (raw)

Unsupervised and online non-stationary obstacle discovery and modeling using a laser range finder

Using laser range finders has shown its efficiency to perform mapping and navigation for mobile robots. However, most of existing methods assume a mostly static world and filter away dynamic aspects while those dynamic aspects are often caused by non-stationary objects which may be important for the robot task. We propose an approach that makes it possible to detect, learn and recognize these objects through a multi-view model, using only a planar laser range finder. We show using a supervised approach that despite the limited information provided by the sensor, it is possible to recognize efficiently up to 22 different object, with a low computing cost while taking advantage of the large field of view of the sensor. We also propose an online, incremental and unsupervised approach that make it possible to continuously discover and learn all kind of dynamic elements encountered by the robot including people and objects.

Tracking and classification of dynamic obstacles using laser range finder and vision

Proc. of the IEEE/RSJ …, 2006

A multi-module architecture to detect, track and classify objects in semi-structured outdoor scenarios for intelligent vehicles is proposed in this paper. In order to fulfill this task it was used the information provided by a laser range finder (LRF) and a monocular camera. The detection and tracking phases are performed in the LRF space, and the object classification methods work both in laser (with a Majority Voting scheme and a Gaussian Mixture Model (GMM) classifier) and in vision spaces (AdaBoost classifier). A sum decision rule based on the Bayes approach is used in order to combine the results of each classification technique, and hence a more reliable object classification is achieved. Experiments using real data confirm the robustness of the proposed architecture.

Moving obstacles detection based on laser range finder measurements

International Journal of Advanced Robotic Systems, 2018

The objective of this article is to propose data processing from laser range finder that will provide simple, fast, and reliable object recognition including moving objects. The whole method is based on four steps: segmentation, simplification, correspondence between consequent measurements, and object classification. Segmentation uses raw data from laser range finder and it is significant in logical connection of related segments. The most important step is simplification which provides data reduction and acceleration of object classification. The output of simplification is an object represented by significant points. Correspondence between consequent measurements is based on kd-tree nearest neighborhood search. The object is then classified by its spatial changes. These changes are evaluated by position of correspondent significant points. Input of proposed procedure is a probabilistic model of laser range finder. In this article, versatile probabilistic model of Hokuyo URM-30 LX...

Laser-based corridor detection for reactive navigation

Industrial Robot: An International Journal, 2008

For mobile robots operating in real-world environments, reactive navigation is a useful complement (or even replacement) to pure plan-based metric navigation. Reactive navigation is performed with respect to local perceived features, rather than a global metric reference frame, and can provide reduced installation costs, increased flexibility, and robustness to changes in the environment. To be effective, however, reactive navigation requires fast and reliable perception of the relevant features in the environment. Corridor-like structures are one of the most common features that are used for this purpose. In this paper, we propose a new method for corridor detection from laser data, based on the Hough transform, which is fast, reliable, and noise tolerant. We describe the algorithm, report an extensive experimental evaluation of its performance, and motivate the research with a real application involving the autonomous operation of a loader vehicle in an underground mine.

A 3D laser range finder for autonomous mobile robots

2001

This paper presents a high quality, low cost 3D laser range finder designed for autonomous mobile systems. The 3D laser is built on the base of a 2D range finder by the extension with a standard servo. The servo is controlled by a computer running RT-Linux. The scan resolution (¢ 5 cm) for a complete 3D scan of an area of 150 (h) £ 90 (v) degree is up to 115000 points and can be grabbed in 12 seconds. Standard resolutions e.g. 150 (h) £ 90 (v) degree with 22500 points are grabbed in 4 seconds. While scanning, different online algorithms for line and surface detection are applied to the data. Object segmentation and detection are done offline after the scan. The implemented software modules detect overhanging objects blocking the path of the robot. With the proposed approach a cheap, precise, reliable and real-time capable 3D sensor for autonomous mobile robots is available and the robot navigation and recognition in real-time is improved.

Characterization of a 2D laser scanner for mobile robot obstacle negotiation

Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292), 2002

This paper presents a characterization study of the Sick LMS 200 laser scanner. A number of parameters, such as operation time, data transfer rate, target surface properties, as well as the incidence angle, which may potentially affect the sensing performance, are investigated. A probabilistic range measurement model is built based on the experimental results. The paper also analyzes the mixed pixels problem of the scanner.

Some applications of laser rangefinder in mobile robotics

Active ranging sensors are the most popular sensors in mobile robotics. One of them, laser rangefinder, has many advantages over other ranging sensors. Despite its considerably high costs, it is a very accurate, reliable and high-speed sensor. Data from laser rangefinder can be used in many ways. This paper shows some techniques that can be useful in solving tasks such as localization, environmental mapping or navigation. Our approach is based on data pre-processing, using a raw filter as well as a smooth filter. Raw filter allows for reduction of missing and invalid measurements and smooth filter smoothes up the data, so the shape of obstacles can be captured more precisely. In this manner, modified data can be used in further tasks, two of which are presented here: detection of extremes and environmental mapping. Detection of extremes covers corners and discontinuities detection. The result of environmental mapping is a global metric map of the environment. Finally, a short analysis of our future work is presented.

High-performance laser range scanner

SPIE Proceedings, 1998

Laser scanners, or ladars, have been used for a number of years for mobile robot navigation. Although previous scanners were sufficient for low-speed navigation, they often did not have the range or angular resolution necessary for mapping at the long distances required by high-speed navigation. Many also did not provide an ample field of view. In this paper we will present the development of state-of-the-art, high speed, high accuracy, laser range scanner technology This work has been a joint effort between CMU (project lead) and K2T (scanning mechanism) in Pittsburgh and Zoller + Friihlich (laser) in Wangen, Germany. The scanner mechanism provides an unobstructed 360' horizontal field of view, and a 30' vertical field of view. Rcsolution of thc scanner is variablc with a maximum resolution of approximately 0.06 degrees per pixel in both azimuth and clcvation. The laser is amplitude-modulated, continuous-wave with an ambiguity interval of 52 meters, a range resolution of I .6 mni, and a maximum pixcl rate of 500 kHz. This paper will focus on the design and performance of the scanner mechanism and will discuss several potential applications for the technology. Onc application, obstacle detection for Automated Highway applications will be discussed in more detail. Example data will bc shown and current mechanism improvements from the CMU prototype will also be discussed.

Obstacle Detection in Smooth High Curvature Terrain

2002

Detection of obstacles for autonomous vehicles is more difficult when the terrain is not locally planar and remains an open problem. We have developed an approach suited for obstacle detection in those cases where the terrain has significant curvature but is smooth enough that the obstacles are discrete. Our system consists of a low-cost scanning laser rangefinder and a novel algorithm that can reliably detect obstacles as small as 15 cm in curving terrain. This paper presents an analysis of the effectiveness of our system and a summary of experimental results from an outdoor mobile robot.

Low cost, low power structured light based obstacle detection

2008 IEEE/ION Position, Location and Navigation Symposium, 2008

We evaluate the capabilities of an inexpensive obstacle detection system consisting of a CCD or CMOS optical sensor, synchronously pulsed laser and supporting hardware and software. The goal is to expand the range of feasible autonomous vehicle applications to include those that are currently impractical due to limitations on the price, weight, or power requirements of their sensor suites. This system constitutes an active, mechanically passive sensor, relying on the mechanical activity of its host platform to sweep out samples from its surroundings. We evaluate sensor configurations in two example host platform designs. The first is a handheld obstacle detector to aid users with vision impairment, while the second is a short range detector used as part of the sensor ensemble for an autonomous ground vehicle. Tradeoffs for both continuous laser fan and single laser pointer configurations are evaluated. Since the geometric relation between the optical sensor and laser is fixed, we establish effective distance and angle between the laser and sensor given required minimum and maximum ranges, spatial resolution, platform velocity and expected velocities of potential obstacles. In situations with sufficient ambient light, range data from the laser return is used to speed the computation of well known computer vision techniques for object detection to yield estimates of obstacle positions within the environment. Pulsing the laser synchronously with a short shutter time on the camera allows operation of the device as an ANSI Z 136 class 1 device since the laser's active duty cycle is highly compressed. This approach renders visible wavelengths effectively invisible to the naked eye.