Vision-based Motion Planning for an Autonomous Motorcycle on Ill-Structured Road

Song, Dezhen; Lee, Hyun Nam; Yi, Jingang; Levandowski, Anthony

doi:10.1109/iros.2006.282438

Cited by 10 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Areas of driveable ground can be extracted in different ways, e.g., vision has been used in several projects [20][21][22] to find driveable regions for unmanned vehicles. In this work the free space from the occupancy grid map is interpreted as ground.…”

Section: Global Segmentation Of Aerial Imagesmentioning

confidence: 99%

Fusion of aerial images and sensor data from a ground vehicle for improved semantic mapping

Persson

Duckett

Lilienthal

2008

Robotics and Autonomous Systems

View full text Add to dashboard Cite

This work investigates the use of semantic information to link ground level occupancy maps and aerial images. A ground level semantic map, which shows open ground and indicates the probability of cells being occupied by walls of buildings, is obtained by a mobile robot equipped with an omnidirectional camera, GPS and a laser range finder. This semantic information is used for local and global segmentation of an aerial image. The result is a map where the semantic information has been extended beyond the range of the robot sensors and predicts where the mobile robot can find buildings and potentially driveable ground.

show abstract

Section: Global Segmentation Of Aerial Imagesmentioning

confidence: 99%

Fusion of aerial images and sensor data from a ground vehicle for improved semantic mapping

Persson

Duckett

Lilienthal

2008

Robotics and Autonomous Systems

View full text Add to dashboard Cite

show abstract

“…The gap between the capabilities of the vision system and the embedded processing system is still a challenging subject. Many proposed systems have been published, such as in [25][26][27][28][29][30]. In these systems, motion planning is integrated with the tracking system in order to improve the overall system capabilities.…”

Section: Introductionmentioning

confidence: 99%

Real-time multi-object detection and tracking for autonomous robots in uncontrolled environments

Said

Ghoniemy

Karam

2012

2012 Seventh International Conference on Computer Engineering &Amp; Systems (ICCES)

View full text Add to dashboard Cite

in this paper a new system is developed for autonomous robots to detect and track multi-objects in uncontrolled environments and in real time for the purpose of decreasing the processing time needed and obtaining better error rates than current systems. To achieve this, a novel multi object tracking algorithm is introduced, implemented and enhanced using multithreading where every thread corresponds to a detected motion area. The implementation considered not only objects tracking but also the object motion estimation to speed up the overall tracking process. In addition, a modified color tracking algorithm is also introduced and integrated in the built system. It is based on the HSV color space. This avoids the problems of overlapping detected motion areas. Experimental results on the built system demonstrate that the proposed system reduced the computational time to approximately 54% compared to published results and reduced the position error to less than 1%.

show abstract

“…A second type of map is based on the roughness of the terrain and is intended to be used for path planning. Closely related work concerns detection of driveable areas for mobile robots using vision [2], [6], [14]. These works do not primarily build maps but use the information for road localisation.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Semantic Mapping with a Virtual Sensor for Building/Nature detection

Persson

Duckett

Valgren

et al. 2007

2007 International Symposium on Computational Intelligence in Robotics and Automation

View full text Add to dashboard Cite

Abstract-In human-robot communication it is often important to relate robot sensor readings to concepts used by humans. We believe that access to semantic maps will make it possible for robots to better communicate information to a human operator and vice versa. The main contribution of this paper is a method that fuses data from different sensor modalities, range sensors and vision sensors are considered, to create a probabilistic semantic map of an outdoor environment. The method combines a learned virtual sensor (understood as one or several physical sensors with a dedicated signal processing unit for recognition of real world concepts) for building detection with a standard occupancy map. The virtual sensor is applied on a mobile robot, combining classifications of sub-images from a panoramic view with spatial information (location and orientation of the robot) giving the likely locations of buildings. This information is combined with an occupancy map to calculate a probabilistic semantic map. Our experiments with an outdoor mobile robot show that the method produces semantic maps with correct labeling and an evident distinction between 'building' objects from 'nature' objects.

show abstract

Vision-based Motion Planning for an Autonomous Motorcycle on Ill-Structured Road

Cited by 10 publications

References 40 publications

Fusion of aerial images and sensor data from a ground vehicle for improved semantic mapping

Fusion of aerial images and sensor data from a ground vehicle for improved semantic mapping

Real-time multi-object detection and tracking for autonomous robots in uncontrolled environments

Probabilistic Semantic Mapping with a Virtual Sensor for Building/Nature detection

Contact Info

Product

Resources

About