Design, implementation, and test of skid steering-based autonomous driving controller for a robotic vehicle with articulated suspension

Abstract. This paper is devoted to the problem of image semantic segmentation for machine vision system of off-road autonomous robotic vehicle. Most modern convolutional neural networks require large computing resources that go beyond the capabilities of many robotic platforms. Therefore, the main drawback of such models is extremely high complexity of the convolutional neural network used, whereas tasks in real applications must be performed on devices with limited resources in real-time. This paper focuses on the practical application of modern lightweight architectures as applied to the task of semantic segmentation on mobile robotic systems. The article discusses backbones based on ResNet18, ResNet34, MobileNetV2, ShuffleNetV2, EfficientNet-B0 and decoders based on U-Net and DeepLabV3 as well as additional components that can increase the accuracy of segmentation and reduce the inference time. In this paper we propose a model using ResNet34 and DeepLabV3 decoding with Squeeze & Excitation blocks that was optimal in terms of inference time and accuracy. We also demonstrate our off-road dataset and simulated dataset for semantic segmentation. Furthermore, we present that using pre-trained weights on simulated dataset achieves to increase 2.7% mIoU on our off-road dataset compared pre-trained weights on the Cityscapes. Moreover, we achieve 75.6% mIoU on the Cityscapes validation set and 85.2% mIoU on our off-road validation set with a speed of 37 FPS for a 1,024×1,024 input on one NVIDIA GeForce RTX 2080 card using NVIDIA TensorRT.

Download Full-text

REAL-TIME SEMANTIC SLAM WITH DCNN-BASED FEATURE POINT DETECTION, MATCHING AND DENSE POINT CLOUD AGGREGATION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b2-2021-399-2021 ◽

2021 ◽

Vol XLIII-B2-2021 ◽

pp. 399-404

Author(s):

B. Vishnyakov ◽

I. Sgibnev ◽

V. Sheverdin ◽

A. Sorokin ◽

P. Masalov ◽

...

Keyword(s):

Neural Networks ◽

Real Time ◽

Semantic Segmentation ◽

Autonomous Driving ◽

Scene Reconstruction ◽

Deep Convolutional Neural Networks ◽

Dense Point ◽

Robotic Vehicle ◽

Semantic Scene ◽

Point Detection

Abstract. In this paper we present the semantic SLAM method based on a bundle of deep convolutional neural networks. It provides real-time dense semantic scene reconstruction for the autonomous driving system of an off-road robotic vehicle. Most state-of-the-art neural networks require large computing resources that go beyond the capabilities of many robotic platforms. We propose an architecture for 3D semantic scene reconstruction on top of the recent progress in computer vision by integrating SuperPoint, SuperGlue, Bi3D, DeepLabV3+, RTM3D and additional module with pre-processing, inference and postprocessing operations performed on GPU. We also updated our simulated dataset for semantic segmentation and added disparity images.

Download Full-text

Skid Steering Based Maneuvering of Robotic Vehicle with Articulated Suspension

SAE International Journal of Passenger Cars - Mechanical Systems ◽

10.4271/2009-01-0437 ◽

2009 ◽

Vol 2 (1) ◽

pp. 645-652 ◽

Cited By ~ 6

Author(s):

Juyong Kang ◽

Wongun Kim ◽

Kyongsu Yi ◽

Soungyong Jung

Keyword(s):

Skid Steering ◽

Robotic Vehicle

Download Full-text

Skid Steering of Robotic Vehicle for Autonomous Applications

2019 International Conference on Electrical Drives & Power Electronics (EDPE) ◽

10.1109/edpe.2019.8883907 ◽

2019 ◽

Author(s):

Robert Dveges ◽

Frantisek Durovsky ◽

Viliam Fedak

Keyword(s):

Skid Steering ◽

Robotic Vehicle

Download Full-text

SEMANTIC SEGMENTATION USING OPTICAL SENSORS IN THE TASK OF AUTONOMOUS DRIVING

Vestnik komp iuternykh i informatsionnykh tekhnologii ◽

10.14489/vkit.2021.11.pp.027-036 ◽

2021 ◽

pp. 27-36

Author(s):

I. V. Sgibnev ◽

B. V. Vishnyakov

Keyword(s):

Optical Sensors ◽

Vision System ◽

Semantic Segmentation ◽

Autonomous Driving ◽

Input Image ◽

Simulated Dataset ◽

Limited Resources ◽

Practical Application ◽

Robotic Vehicle ◽

Validation Set

This paper is devoted to the problem of image semantic segmentation for machine vision system of off-road autonomous robotic vehicle. Most modern convolutional neural networks require large computing resources that go beyond the capabilities of many robotic platforms. Therefore, the main drawback of such models is extremely high complexity of the convolutional neural network used, whereas tasks in real applications must be performed on devices with limited resources in real-time. This paper focuses on the practical application of modern lightweight architectures as applied to the task of semantic segmentation on mobile robotic systems. The article discusses backbones based on ResNet18, ResNet34, MobileNetV2, ShuffleNetV2, EfficientNet-B0 and decoders based on U-Net, DeepLabV3 and DeepLabV3+ as well as additional components that can increase the accuracy of segmentation and reduce the inference time. In this paper we propose a model using ResNet34 enconding and DeepLabV3+ decoding with Squeeze & Excitation blocks that was optimal in terms of inference time and accuracy. We also demonstrate our off-road dataset and simulated dataset for semantic segmentation. Furthermore, we increased mIoU metric by 2.6 % on our off-road dataset using pretrained weights on simulated dataset, compared with mIoU metric using pretrained weights on the Cityscapes. Moreover, we achieved 76.1 % mIoU on the Cityscapes validation set and 85.4 % mIoU on our off-road validation set at 37 FPS (Frames per Second) for an input image of 1024×1024 size on one NVIDIA GeForce RTX 2080 card using NVIDIA TensorRT inference framework.

Download Full-text