Cognitive Radar System for Obstacle Avoidance Using In-Motion Memory-Aided Mapping

Guo, Liyong; Antoniou, Michail; Baker, C.J.

doi:10.1109/radarconf2043947.2020.9266655

Cited by 2 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a variety of sensors that can be used for obstacle detection. Some of the most popular sensors [23] are infrared sensors [24,25], ultrasonic sensors [26,27], cameras [28,29], radars [30,31], or LiDaRs [32,33].…”

Section: Related Workmentioning

confidence: 99%

Simultaneous Object Detection and Distance Estimation for Indoor Autonomous Vehicles

Azurmendi,

Zulueta,

Lopez-Guede

et al. 2023

Electronics

View full text Add to dashboard Cite

Object detection is an essential and impactful technology in various fields due to its ability to automatically locate and identify objects in images or videos. In addition, object-distance estimation is a fundamental problem in 3D vision and scene perception. In this paper, we propose a simultaneous object-detection and distance-estimation algorithm based on YOLOv5 for obstacle detection in indoor autonomous vehicles. This method estimates the distances to the desired obstacles using a single monocular camera that does not require calibration. On the one hand, we train the algorithm with the KITTI dataset, which is an autonomous driving vision dataset that provides labels for object detection and distance prediction. On the other hand, we collect and label 100 images from a custom environment. Then, we apply data augmentation and transfer learning to generate a fast, accurate, and cost-effective model for the custom environment. The results show a performance of mAP0.5:0.95 of more than 75% for object detection and 0.71 m of mean absolute error in distance prediction, which are easily scalable with the labeling of a larger amount of data. Finally, we compare our method with other similar state-of-the-art approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Simultaneous Object Detection and Distance Estimation for Indoor Autonomous Vehicles

Azurmendi,

Zulueta,

Lopez-Guede

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Figure 11a is the WMM (10), accumulated from 26 frames of radar data. The figure shows both obstacles are now clearly detected, while their distribution is indicative of the variability of the scattering from the cylindrical obstacle.…”

Section: Algorithm Validationmentioning

confidence: 99%

“…However, collisions happened in some of the trials and the trajectories of the robot were not smooth. Here in this study, short‐term memories are generated from prior radar data and formed into ‘world memory map’ (WMM) [10]. The process is part inspired by the in‐motion mapping concept [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Memory‐augmented cognitive radar for obstacle avoidance using nearest steering vector search

Guo

Antoniou

Baker

2020

IET Radar Sonar & Navi

Self Cite

View full text Add to dashboard Cite

This study describes a cognitive radar architecture with application to real‐time obstacle avoidance in mobile robotic platforms. The concept of a world memory map is introduced as a means of providing an enhanced perception of the environment around the robotic platform. This is combined with a specially designed obstacle avoidance algorithm, Nearest Steering Vector Searching, all capable of operating in real‐time. The study analytically derives the radar signal processing algorithm, starting from range‐angle maps, so that a collision free course to a set destination point can be robustly navigated. Finally, the performance of this cognitive approach is examined through a number of proof‐of‐concept experiments using a commercial off‐the‐shelf radar mounted on a mobile ground robotic platform.

show abstract

Cognitive Radar System for Obstacle Avoidance Using In-Motion Memory-Aided Mapping

Cited by 2 publications

References 13 publications

Simultaneous Object Detection and Distance Estimation for Indoor Autonomous Vehicles

Simultaneous Object Detection and Distance Estimation for Indoor Autonomous Vehicles

Memory‐augmented cognitive radar for obstacle avoidance using nearest steering vector search

Contact Info

Product

Resources

About