Real-time map refinement by fusing sonar and active stereo-vision

Wallner, Frank; Graf, René; Dillmann, Ruediger

doi:10.1109/robot.1995.525705

Cited by 18 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, sensor fusion methods are implemented to generate higher quality maps in previous works. Some use stereo vision with laser scanner [1] [2], and some use stereo vision with sonar [3] [4]. From the results of these studies, we find that even though sonar sensors cannot provide precise range data, it can compensate the sensing results of vision and laser scanner, especially when they cannot detect transparent objects directly.…”

Section: A Ideas and Related Workmentioning

confidence: 99%

Sensor fusion based vSLAM system for 3D environment grid map construction

Luo

Hsiao

Xie

2013

2013 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

The objective of this paper is to develop a mobile robot system to construct stereo vision and sonar fusion grid maps of 3D environment structure, which is based on a visual simultaneously localization and mapping (vSLAM) system. We first solve the problem of large textureless area for stereo camera by projecting laser dots onto them, and design the system algorithm to avoid the visual features of vSLAM disturbed by the projected laser dots. Meanwhile, some functions are integrated to make the projection efficient and avoid laser dots projected toward humans. The 3D grid map construction methods are also well designed to ensure the confidence of each grid even when stereo and sonar range data are noisy. We successfully demonstrate the concept through experiments, and the grid map is sufficient for future navigation and path planning tasks.

show abstract

Section: A Ideas and Related Workmentioning

confidence: 99%

Sensor fusion based vSLAM system for 3D environment grid map construction

Luo

Hsiao

Xie

2013

2013 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

show abstract

“…If the values are calculated off-line for reuse, a table of size O(2"') is needed. As a result, occupancy grids are feasible only within a local region [14] since the map may not reflect in time dynamic changes in the environment. On the other hand, computing the vector field histograms [3] is simple, but the resulting model is only good for local obstacle avoidance rather than global path planning.…”

Section: Occupancy Probability Profilementioning

confidence: 99%

A graph-based exploration strategy of indoor environments by an autonomous mobile robot

Hsu

Hwang

Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146)

View full text Add to dashboard Cite

This paper presents a provably complete strategy f o r indoor environment exploration by a n autonomous mobile robot. Without prior knowledge about the environment, the strategy guarantees the construction of a grid-based map of the entire reachable area within a bounded region. Multiple m a p representations are utilized inc6uding a topological grid m a p f o r guiding the exploration process, a modified occupancy grid f o r fusing data f r o m multiple range sensors, and a hierarchy of grids f o r real-time navigation. Experiments using a Nomad 200TM robot have shown accurate map construction while navigating at a steady speed of 0..2m/sec.

show abstract

Real Time Tracking and Monitoring of Human Behavior in an Indoor Environment

Habib

Lecture Notes Electrical Engineering

View full text Add to dashboard Cite

Real-time map refinement by fusing sonar and active stereo-vision

Cited by 18 publications

References 9 publications

Sensor fusion based vSLAM system for 3D environment grid map construction

Sensor fusion based vSLAM system for 3D environment grid map construction

A graph-based exploration strategy of indoor environments by an autonomous mobile robot

Real Time Tracking and Monitoring of Human Behavior in an Indoor Environment

Contact Info

Product

Resources

About