TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection
This work addresses the reliability issues of cameras and LiDAR in low-light and adverse weather for autonomous systems, offering a complementary radar-based solution, though it appears incremental as it builds on existing transformer and radar detection methods.
The paper tackles the problem of radar-based object detection for autonomous driving and robotics, which is challenging due to low resolution and noise in radar data, by introducing TransRAD, a model that uses a Retentive Vision Transformer to improve feature learning from radar data, resulting in state-of-the-art performance with higher accuracy, faster inference, and reduced complexity.
Despite significant advancements in environment perception capabilities for autonomous driving and intelligent robotics, cameras and LiDARs remain notoriously unreliable in low-light conditions and adverse weather, which limits their effectiveness. Radar serves as a reliable and low-cost sensor that can effectively complement these limitations. However, radar-based object detection has been underexplored due to the inherent weaknesses of radar data, such as low resolution, high noise, and lack of visual information. In this paper, we present TransRAD, a novel 3D radar object detection model designed to address these challenges by leveraging the Retentive Vision Transformer (RMT) to more effectively learn features from information-dense radar Range-Azimuth-Doppler (RAD) data. Our approach leverages the Retentive Manhattan Self-Attention (MaSA) mechanism provided by RMT to incorporate explicit spatial priors, thereby enabling more accurate alignment with the spatial saliency characteristics of radar targets in RAD data and achieving precise 3D radar detection across Range-Azimuth-Doppler dimensions. Furthermore, we propose Location-Aware NMS to effectively mitigate the common issue of duplicate bounding boxes in deep radar object detection. The experimental results demonstrate that TransRAD outperforms state-of-the-art methods in both 2D and 3D radar detection tasks, achieving higher accuracy, faster inference speed, and reduced computational complexity. Code is available at https://github.com/radar-lab/TransRAD