MTR++: Multi-Agent Motion Prediction With Symmetric Scene Modeling and Guided Intention Querying.

Motion prediction is crucial for autonomous driving systems to understand complex driving scenarios and make informed decisions. However, this task is challenging due to the diverse behaviors of traffic participants and complex environmental contexts. In this paper, we propose Motion TRansformer (MTR) frameworks to address these challenges.

ST3D++: Denoised Self-Training for Unsupervised Domain Adaptation on 3D Object Detection.

In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object detection. ST3D++ aims at reducing noise in pseudo label generation as well as alleviating the negative impacts of noisy pseudo labels on model training. First, ST3D++ pre-trains the 3D object detector on the labeled source domain with random object scaling (ROS) which is designed to reduce target domain pseudo label noise arising from object scale bias of the source domain.

From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network.

3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network (Part- A net). The whole framework consists of the part-aware stage and the part-aggregation stage.

Applicability of Yielding-Resisting Sand Column and Three-Dimensional Coordination Support in Stopes.

In view of the existing problems of stope roadways, which are difficult to maintain under the influence of high ground and mining-induced stresses, the structural characteristics and movement regularities of stopes surrounding rocks were analysed. Through the construction of a three-dimensional mechanical model of the coordination support of a stope, the adaptability index of the support in stope is presented, and its mechanism of operation is expounded. Yielding-resisting sand column (YRSC) sidewall-support technology with satisfactory compressibility and supporting strength was developed.