Learning Automated Driving in Complex Intersection Scenarios Based on Camera Sensors: A Deep Reinforcement Learning Approach

Li, Guofa; Lin, Si-Yan; Shen, Li; Qu, Xingda

doi:10.1109/jsen.2022.3146307

Cited by 19 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the oppression of data efficiency compels the regular CNN visual encoder to extract object features unsteadily. In consideration of the outstanding performance of the Transformer, many works have studied the combination of Transformer and RL [ 35 , 36 , 37 , 38 , 39 ]. This type of combination made some improvements in partial visual-based tasks, but the preponderance of ViT is not steady and even worse than the original visual encoder which may be due to the massive data requirements in general tasks training.…”

Section: Related Workmentioning

confidence: 99%

Vision-Based Efficient Robotic Manipulation with a Dual-Streaming Compact Convolutional Transformer

Guo

Song

Ding

et al. 2023

Sensors

View full text Add to dashboard Cite

Learning from visual observation for efficient robotic manipulation is a hitherto significant challenge in Reinforcement Learning (RL). Although the collocation of RL policies and convolution neural network (CNN) visual encoder achieves high efficiency and success rate, the method general performance for multi-tasks is still limited to the efficacy of the encoder. Meanwhile, the increasing cost of the encoder optimization for general performance could debilitate the efficiency advantage of the original policy. Building on the attention mechanism, we design a robotic manipulation method that significantly improves the policy general performance among multitasks with the lite Transformer based visual encoder, unsupervised learning, and data augmentation. The encoder of our method could achieve the performance of the original Transformer with much less data, ensuring efficiency in the training process and intensifying the general multi-task performances. Furthermore, we experimentally demonstrate that the master view outperforms the other alternative third-person views in the general robotic manipulation tasks when combining the third-person and egocentric views to assimilate global and local visual information. After extensively experimenting with the tasks from the OpenAI Gym Fetch environment, especially in the Push task, our method succeeds in 92% versus baselines that of 65%, 78% for the CNN encoder, 81% for the ViT encoder, and with fewer training steps.

show abstract

Section: Related Workmentioning

confidence: 99%

Vision-Based Efficient Robotic Manipulation with a Dual-Streaming Compact Convolutional Transformer

Guo

Song

Ding

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In general, these methods use the design of an object to create boundary containers for recognizing the objects based on the environment [23,24]. However, camera sensors suffer from various lighting conditions levels and have insufficient knowledge of regions, directions, object shape, and structure, resulting in inaccurate object-area identifications [25,26].…”

Section: Introductionmentioning

confidence: 99%

Real-Time 3D Object Detection and Classification in Autonomous Driving Environment Using 3D LiDAR and Camera Sensors

Arikumar¹,

Kumar

Gadekallu

et al. 2022

Electronics

View full text Add to dashboard Cite

The rapid development of Autonomous Vehicles (AVs) increases the requirement for the accurate prediction of objects in the vicinity to guarantee safer journeys. For effectively predicting objects, sensors such as Three-Dimensional Light Detection and Ranging (3D LiDAR) and cameras can be used. The 3D LiDAR sensor captures the 3D shape of the object and produces point cloud data that describes the geometrical structure of the object. The LiDAR-only detectors may be subject to false detection or even non-detection over objects located at high distances. The camera sensor captures RGB images with sufficient attributes that describe the distinct identification of the object. The high-resolution images produced by the camera sensor benefit the precise classification of the objects. However, hindrances such as the absence of depth information from the images, unstructured point clouds, and cross modalities affect assertion and boil down the environmental perception. To this end, this paper proposes an object detection mechanism that fuses the data received from the camera sensor and the 3D LiDAR sensor (OD-C3DL). The 3D LiDAR sensor obtains point clouds of the object such as distance, position, and geometric shape. The OD-C3DL employs Convolutional Neural Networks (CNN) for further processing point clouds obtained from the 3D LiDAR sensor and the camera sensor to recognize the objects effectively. The point cloud of the LiDAR is enhanced and fused with the image space on the Regions of Interest (ROI) for easy recognition of the objects. The evaluation results show that the OD-C3DL can provide an average of 89 real-time objects for a frame and reduces the extraction time by a recall rate of 94%. The average processing time is 65ms, which makes the OD-C3DL model incredibly suitable for the AVs perception. Furthermore, OD-C3DL provides mean accuracy for identifying automobiles and pedestrians at a moderate degree of difficulty is higher than that of the previous models at 79.13% and 88.76%.

show abstract

Multi-sensor based strategy learning with deep reinforcement learning for unmanned ground vehicle

Luo

2023

International Journal of Intelligent Networks

View full text Add to dashboard Cite

Learning Automated Driving in Complex Intersection Scenarios Based on Camera Sensors: A Deep Reinforcement Learning Approach

Cited by 19 publications

References 40 publications

Vision-Based Efficient Robotic Manipulation with a Dual-Streaming Compact Convolutional Transformer

Vision-Based Efficient Robotic Manipulation with a Dual-Streaming Compact Convolutional Transformer

Real-Time 3D Object Detection and Classification in Autonomous Driving Environment Using 3D LiDAR and Camera Sensors

Multi-sensor based strategy learning with deep reinforcement learning for unmanned ground vehicle

Contact Info

Product

Resources

About