Prior studies in the field of motion predictions for autonomous driving tend to focus on finding a trajectory that is close to the ground truth trajectory, which is highly biased toward straight maneuvers. Such problem formulations and imbalanced distribution of datasets, however, frequently lead to a loss of diversity and biased trajectory predictions. Therefore, they are unsuitable for real-world autonomous driving, where diverse and road-dependent multimodal trajectory predictions are critical for safety. To this end, this study proposes a novel trajectory prediction model that ensures map-adaptive diversity and accommodates geometric constraints. A two-stage trajectory prediction architecture with a novel trajectory candidate proposal module, Trajectory Prediction Attention (TPA) , which is trained with Lane Loss , encourages multiple trajectories to be diversely distributed in a map-aware manner. Furthermore, the diversity of multiple trajectory predictions cannot be properly evaluated by existing metrics, and thus a novel quantitative evaluation metric, termed the minimum lane final displacement error (minLaneFDE), is also proposed to evaluate the diversity as well as the accuracy of multiple trajectory predictions. Experiments conducted on the Argoverse dataset show that the proposed method simultaneously improves the diversity and accuracy of the predicted trajectories.
29 November 2022 in IEEE Transactions on Intelligent Transportation Systems
Recent advances in monocular 3D detection leverage a depth estimation network explicitly as an intermediate stage of the 3D detection network. Depth map approaches yield more accurate depth to objects than other methods thanks to the depth estimation network trained on a large-scale dataset. However, depth map approaches can be limited by the accuracy of the depth map, and sequentially using two separated networks for depth estimation and 3D detection significantly increases computation cost and inference time. In this work, we propose a method to boost the RGB image-based 3D detector by jointly training the detection network with a depth prediction loss analogous to the depth estimation task. In this way, our 3D detection network can be supervised by more depth supervision from raw LiDAR points, which does not require any human annotation cost, to estimate accurate depth without explicitly predicting the depth map. Our novel object-centric depth prediction loss focuses on depth around foreground objects, which is important for 3D object detection, to leverage pixel-wise depth supervision in an object-centric manner. Our depth regression model is further trained to predict the uncertainty of depth to represent the 3D confidence of objects. To effectively train the 3D detector with raw LiDAR points and to enable end-to-end training, we revisit the regression target of 3D objects and design a network architecture. Extensive experiments on KITTI and nuScenes benchmarks show that our method can significantly boost the monocular image-based 3D detector to outperform depth map approaches while maintaining the real-time inference speed.
To make intelligent decisions in an autonomous vehicle, the system must predict the future reactions of surrounding vehicles for any given action plan of the ego vehicle. However, learning reactive trajectories is challenging due to scant action-reaction pair data. That is, building a dataset with multiple action-reaction pairs for an identical scene history is impossible in reality. Here, we propose a semi-supervised learning framework with auxiliary structures to handle this problem. The proposed training framework has two modules: Action Reconstructor and Identifier modules with corresponding loss functions referred to as the Reconstruction Loss and Association Loss . In addition to the conventional supervised approach pertaining to readily available data, the Action Reconstructor module is employed to learn the dependencies on the ego vehicle in an unsupervised manner. Furthermore, reaction trajectory data corresponding to the augmented future trajectories of the ego vehicle are not available, meaning that the model must be trained in an unsupervised manner as well. The main idea of the proposed unsupervised learning method is to find the identity feature vector from both history and future trajectories and associate these features for each vehicle. This idea is realized by introducing the Identifier network and the Association Loss , which are used only during the training process. Interestingly, experimental results show that plausible reaction can be predicted for the augmented future trajectory of the ego vehicle, which indicates that the network can generalize the interactive behavior of vehicles from a partially labelled dataset.