Author name cluster

Junlan Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

ICRA Conference 2025 Conference Paper

Scene-Aware Explainable Multimodal Trajectory Prediction

Pei Liu
Haipeng Liu
Xingyu Liu
Yiqun Li
Junlan Chen
Yangfan He
Jun Ma 0008

Advancements in intelligent technologies have significantly improved navigation in complex traffic environments by enhancing environment perception and trajectory prediction for automated vehicles. However, current research often overlooks the joint reasoning of scenario agents and lacks explainability in trajectory prediction models, limiting their practical use in real-world situations. To address this, we introduce the Explainable Conditional Diffusion-based Multimodal Trajectory Prediction (DMTP) model, which is designed to elucidate the environmental factors influencing predictions and reveal the underlying mechanisms. Our model integrates a modified conditional diffusion approach to capture multimodal trajectory patterns and employs a revised Shapley Value model to assess the significance of global and scenario-specific features. Experiments using the Waymo Open Motion Dataset demonstrate that our explainable model excels in identifying critical inputs and significantly outperforms baseline models in accuracy. Moreover, the factors identified align with the human driving experience, underscoring the model's effectiveness in learning accurate predictions. Code is available in our open-source repository: https://github.com/ocean-luna/Explainable-Prediction.

Details

EAAI Journal 2025 Journal Article

Towards open-world recognition: Critical problems and challenges

Ke Wang
Zhikang Li
Yang Chen
Wenjie Dong
Junlan Chen

With the emergence of rich classification models and high computing power, recognition systems are widely used in various fields. Unfortunately, as the scale of open systems increases, the assumption of a closed-world will lead to the failure of fragile models because almost all machine learning based recognition algorithms are evaluated as implicit “closed-set”. Comparing with classical methods, open-world learning can address concerns in dynamic environments where the input data (size, category, etc.) is changing rapidly. Nevertheless, there still lacks a thorough review of recent advances in open-world recognition. Therefore, we provide an in-depth discussion of open-world recognition based on some recent works. First, we propose a learning framework for open-world recognition, and analyze the challenges from three aspects: domain shift, limits on the amount of labeled data and perception scene with dynamic changes. Secondly, we evaluate the current state of the art, summarize the intersection of various methods and find out some existing problems. Finally, we discuss the limitations of current procedures and new technologies as well as future directions in order to make meaningful progress. This article will help researchers understand Open-world learning and the possibilities of extending research into appropriate areas.

Details DOI

EAAI Journal 2023 Journal Article

PVF-DectNet: Multi-modal 3D detection network based on Perspective-Voxel fusion

Ke Wang
Tianqiang Zhou
Zhichuang Zhang
Tao Chen
Junlan Chen

The detection of small objects such as pedestrians still poses challenges to the LiDAR-based 3D object detection due to the sparseness and disorder of point clouds. Conversely, images from cameras can provide rich semantic information, which makes these small-sized objects easy to be detected. To take use of the advantages of both devices to achieve better 3D object detection, research on the fusion of LiDAR and camera information is now being conducted. The existing fusion methods between point clouds and image are normally weighed more on the point clouds. Hence the semantic information of images is not fully utilized. We propose a new fusion method named PVFusion to try to fuse more image features. We first divide each point into a separate perspective voxel and project the voxel onto the image feature maps. Then the semantic feature of the perspective voxel is fused with the geometric feature of the point. A 3D object detection model (PVF-DectNet) is designed using PVFusion. During training we employ the ground truth paste (GT-Paste) data augmentation and solve the occlusion problem caused by newly added object. The KITTI validation set is used to validate the PVF-DectNet, which shows 3. 6% AP improvement over the other feature fusion methods in pedestrian detection. On the KITTI test set, the PVF-DectNet outperforms the other multi-modal SOTA methods by 2. 2% AP in pedestrian detection. And PVFusion shows better detection performance for sparse point clouds than PointFusion in both car and pedestrian categories. As for 32 beams LiDAR scene, there are 4. 2% AP increment in moderate difficulty car category and 5. 2% mAP improvement in pedestrian category.

Details DOI