End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neu-ral networks render them impractical for deployment on resource-constrained systems, which unavoidably requires more computational time and resources during reference. To handle this, knowledge distillation offers a promising approach that compresses models by enabling a smaller stu-dent model to learn from a larger teacher model. Neverthe-less, how to apply knowledge distillation to compress motion planners has not been explored so far. In this paper, we propose PlanKD, the first knowledge distillation frame-work tailored for compressing end-to-end motion planners. First, considering that driving scenes are inherently complex, often containing planning-irrelevant or even noisy in-formation, transferring such information is not beneficial for the student planner. Thus, we design an information bottleneck based strategy to only distill planning-relevant information, rather than transfer all information indiscrim-inately. Second, different waypoints in an output planned trajectory may hold varying degrees of importance for motion planning, where a slight deviation in certain crucial waypoints might lead to a collision. Therefore, we devise a safety-aware waypoint-attentive distillation module that as-signs adaptive weights to different waypoints based on the importance, to encourage the student to accurately mimic more crucial waypoints, thereby improving overall safety. Experiments demonstrate that our PlanKD can boost the performance of smaller planners by a large margin, and significantly reduce their reference time.

Trajectory prediction plays a significant role in autonomous driving, with current challenges primarily focused on capturing complex interactions in traffic scenes. Previous methods usually directly encode non-interactive and interactive information together, and then decode them for trajectory prediction. However, given the complexity inherent property in the trajectory generation process (e.g., the generation of trajectory points are influenced by the interactions among multiple moving agents, as well as the interactions between agents and the static environment), previous approaches fail to precisely capture separate variations of the trajectory generation process. In this paper, we propose a general and plug-and-play feature decoupling framework for trajectory prediction called FDNet, which can learn the interactive and non-interactive factors in the latent space to capture separate variations of the trajectory generation process. At its core, FDNet is comprised of a Non-interactive Feature Extraction Module to extract non-interactive features, and an Interactive Feature Decoupling Module to decouple interactive features. Extensive experiments conducted on Argoverse and nuScenes demonstrate that FDNet significantly improves the performance of existing methods.

This work focuses on the sample collection in reinforcement learning (RL), where the interaction with the environment is typically time-consuming and extravagantly expensive. In order to collect samples in a more valuable way, we propose a confidence-based sampling strategy based on the optimal computing budget allocation algorithm (OCBA), which actively allocates the computing efforts to actions with different predictive uncertainties. We estimate the uncertainty with ensembles and generalize them from tabular representations to function approximations. The OCBA-based sampling strategy could be easily integrated into various off-policy RL algorithms, where we take Q-learning, DQN, and SAC as examples to show the incorporation. Besides, we provide the theoretical analysis towards convergence and evaluate the algorithms experimentally. According to the experiments, the incorporated algorithms obtain remarkable gains compared with modern ensemble-based RL algorithms.Note to Practitioners—Reinforcement learning is a powerful tool for handling sequential decision-making problems, e.g., autonomous driving and robotics control, where the behaviors typically have a long-term effect on future events. However, although RL achieves human-level control in some tasks, it severely suffers from low sample efficiency. Therefore, implementing RL in some practical areas, e.g., healthcare and rescue, is extremely hard due to the requirement of massive samples. This work aims to enhance the exploration of RL by incorporating OCBA, which provides an asymptotically optimal data-collection strategy for simulation-based optimization. Based on ensemble-based uncertainty estimation and OCBA-based action selection, the incorporated RL algorithms show competitive performance on many benchmarks and significantly reduce the sampling efforts during iterations.

Predicting the future motion of road participants is crucial for autonomous driving but is extremely challenging due to staggering motion uncertainty. Recently, most motion forecasting methods resort to the goal-based strategy, i.e., predicting endpoints of motion trajectories as conditions to regress the entire trajectories, so that the search space of solution can be reduced. However, accurate goal coordinates are hard to predict and evaluate. In addition, the point representation of the destination limits the utilization of a rich road context, leading to inaccurate prediction results in many cases. Goal area, i.e., the possible destination area, rather than goal coordinate, could provide a more soft constraint for searching potential trajectories by involving more tolerance and guidance. In view of this, we propose a new goal area-based framework, named Goal Area Network (GANet), for motion forecasting, which models goal areas as preconditions for trajectory prediction, performing more robustly and accurately. Specifically, we propose a GoICrop (Goal Area of Interest) operator to effectively aggregate semantic lane features in goal areas and model actors' future interactions as feedback, which benefits a lot for future trajectory estimations. GANet ranks the 1st on the leaderboard of Argoverse Challenge among all public literature (till the paper submission). Code will be available at https://github.com/kingwmk/GANet.

The objective of pedestrian trajectory prediction is to estimate the future paths of pedestrians by leveraging historical observations, which plays a vital role in ensuring the safety of self-driving vehicles and navigation robots. Previous works usually rely on a sufficient amount of observation time to accurately predict future trajectories. However, there are many real-world situations where the model lacks sufficient time to observe, such as when pedestrians abruptly emerge from blind spots, resulting in inaccurate predictions and even safety risks. Therefore, it is necessary to perform trajectory prediction based on instantaneous observations, which has rarely been studied before. In this paper, we propose a Bi-directional Consistent Diffusion framework tailored for instantaneous trajectory prediction, named BCDiff. At its heart, we develop two coupled diffusion models by designing a mutual guidance mechanism which can bidirectionally and consistently generate unobserved historical trajectories and future trajectories step-by-step, to utilize the complementary information between them. Specifically, at each step, the predicted unobserved historical trajectories and limited observed trajectories guide one diffusion model to generate future trajectories, while the predicted future trajectories and observed trajectories guide the other diffusion model to predict unobserved historical trajectories. Given the presence of relatively high noise in the generated trajectories during the initial steps, we introduce a gating mechanism to learn the weights between the predicted trajectories and the limited observed trajectories for automatically balancing their contributions. By means of this iterative and mutually guided generation process, both the future and unobserved historical trajectories undergo continuous refinement, ultimately leading to accurate predictions. Essentially, BCDiff is an encoder-free framework that can be compatible with existing trajectory prediction models in principle. Experiments show that our proposed BCDiff significantly improves the accuracy of instantaneous trajectory prediction on the ETH/UCY and Stanford Drone datasets, compared to related approaches.

Pedestrian trajectory prediction is a hot research topic in many applications, such as video surveillance and autonomous driving. Although many efforts have been done on this topic, there are still many challenges, including accumulated prediction errors, insufficient training data usage, and future-past incompatibility. To overcome these challenges, we propose a novel trajectory prediction method, called CSIR, which consists of a cascaded sliding conditional variational autoencoder (CS-CVAE) module and an iterative future-past social compatible rethinking (I-SCR) module. The CS-CVAE module reduces the accumulated prediction errors by using cascaded prediction models for the early future time steps. In this way, the training losses of the early time steps are separately considered and minimized from the later losses. For the following time steps in CS-CVAE, a sliding prediction model with a longer observation time span is used and additional data from the future time span can be collected for training. On the other hand, the I-SCR module generates offsets to improve the predictions iteratively by checking the interaction compatibility between the predicted trajectories and the past trajectories, which resembles with the human rethinking mechanism in motion planning. Experiments results on two widely explored pedestrian trajectory prediction datasets, Stanford Drone Dataset (SDD) and ETH/UCY, show that the proposed method surpasses previous state-of-the-art methods by notable margins.

Motion prediction from raw LiDAR sensor data has drawn increasing attention and led to a surge of studies following two main paradigms. One paradigm is global motion paradigm, which simultaneously detects objects from point clouds and predicts the trajectories of each object in the future. The other paradigm is local motion paradigm, which directly performs dense motion prediction pointwisely. We observe that global motion prediction can benefit from local motion representation, since it contains rich local displacement contexts that are not explicitly exploited in global motion prediction. Correspondingly, local motion prediction can benefit from global motion representation, since it provides object contexts to improve prediction consistency inside an object. However, the complement of these two motion representations has not fully explored in the literature. To this end, we propose Hybrid Motion Representation Learning (HyMo), a unified framework to address the problem of motion prediction by making the best of both global and local motion cues. We have conducted extensive experiments on nuScenes dataset. The experimental results demonstrate that the learned hybrid motion representation achieves state-of-the-art performance on both global and local motion prediction tasks.

Autonomous vehicles (AVs) need to make driving decisions to interact with other traffic participants. By adapting to different scenarios with specific parameters, traditional strategies attempt to leverage rule-based methods to solve the decision problems. In this paper, we present a novel reinforcement learning method for resolving interaction uncertainty in the decision-making problem. We construct prior knowledge by introducing traffic regulations and constraints and then converting them into rules that govern the learning of driving policies. To promote safe driving, a safety-aware module equipped with a mathematical collision correlation analysis is developed to anticipate and handle dangerous traffic scenarios. A realistic scenario involving an AV approaching a crosswalk is used to validate the proposed method. The experimental results indicate that the proposed method improves driving safety and efficiency significantly when compared to alternative approaches and can be generalized to more difficult scenarios.

Trajectory prediction of multiple agents in a crowded scene is an essential component in many applications, including intelligent monitoring, autonomous robotics, and self-driving cars. Accurate agent trajectory prediction remains a significant challenge because of the complex dynamic interactions among the agents and between them and the surrounding scene. To address the challenge, we propose a decoupled attention-based spatial-temporal modeling strategy in the proposed trajectory prediction method. The past and current interactions among agents are dynamically and adaptively summarized by two separate attention-based networks and have proven powerful in improving the prediction accuracy. Moreover, it is optional in the proposed method to make use of the road map and the plan of the ego-agent for scene-compliant and accurate predictions. The road map feature is efficiently extracted by a convolutional neural network, and the features of the ego-agent’s plan is extracted by a gated recurrent network with an attention module based on the temporal characteristic. Experiments on benchmark trajectory prediction datasets demonstrate that the proposed method is effective when the ego-agent plan and the the surrounding scene information are provided and achieves state-of-the-art performance with only the observed trajectories.

Unsupervised active learning has been an active research topic in machine learning community, with the purpose of choosing representative samples to be labelled in an unsupervised manner. Previous works usually take the minimization of data reconstruction loss as the criterion to select representative samples which can better approximate original inputs. However, data are often drawn from low-dimensional subspaces embedded in an arbitrary high-dimensional space in many scenarios, thus it might severely bring in noise if attempting to precisely reconstruct all entries of one observation, leading to a suboptimal solution. In view of this, this paper proposes a novel unsupervised Active Learning model via Subspace Learning, called ALSL. In contrast to previous approaches, ALSL aims to discovery the low-rank structures of data, and then perform sample selection based on learnt low-rank representations. To this end, we devise two different strategies and propose two corresponding formulations to perform unsupervised active learning with and under low-rank sample representations respectively. Since the proposed formulations involve several non-smooth regularization terms, we develop a simple but effective optimization procedure to solve them. Extensive experiments are performed on five publicly available datasets, and experimental results demonstrate the proposed first formulation achieves comparable performance with the state-of-the-arts, while the second formulation significantly outperforms them, achieving a 13\% improvement over the second best baseline at most.

Trajectory prediction is a fundamental task in many real applications such as autonomous robotics and video surveillance. In this paper, we propose a novel vision-based trajectory prediction method which is able to extract the interactive features by active global interaction-aware drivable space learning. The learned global interaction-aware drivable spaces denote the areas with low occupation probabilities, which provide the regions and directions that the agents can move into. Specifically, our method describes a sequence of motion states, i.e. the location, the velocity and the acceleration, as occupancy grid maps, and then use them to train the deep learning model in the supervised manner. Moreover, an interactive loss for training the inference net of drivable spaces and trajectory prediction net simultaneously is introduced. Comparisons with state-of-the-art methods on benchmark datasets demonstrate the effectiveness of the proposed method.

Motion prediction of multiple agents in a dynamic scene is a crucial component in many real applications, including intelligent monitoring and autonomous driving. Due to the complex interactions among the agents and their interactions with the surrounding scene, accurate trajectory prediction is still a great challenge. In this paper, we propose a new method for robust trajectory prediction of multiple intelligent agents in a dynamic scene. The input of the method includes the observed trajectories of all agents, and optionally, the planning of the ego-agent and the surrounding high definition map at every time steps. Given observed trajectories, an efficient approach in a star computational topology is utilized to compute both the spatiotemporal interaction features and the current interaction features between the agents, where the time complexity scales linearly to the number of agents. Moreover, on an autonomous vehicle, the proposed prediction method can make use of the planning of ego-agent to improve the modeling of the interaction between surrounding agents. To increase the robustness to upstream perception noises, at the training stage, we randomly mask out the input data, a.k.a. the points on the observed trajectories of agents and the lane sequence. Experiments on autonomous driving and pedestrian-walking datasets demonstrate that the proposed method is not only effective when the planning of ego-agent and the high definition map are provided, but also achieves state-of-the-art performance with only the observed trajectories.

Pedestrian trajectory prediction is crucial for many important applications. This problem is a great challenge because of complicated interactions among pedestrians. Previous methods model only the pairwise interactions between pedestrians, which not only oversimplifies the interactions among pedestrians but also is computationally inefficient. In this paper, we propose a novel model StarNet to deal with these issues. StarNet has a star topology which includes a unique hub network and multiple host networks. The hub network takes observed trajectories of all pedestrians to produce a comprehensive description of the interpersonal interactions. Then the host networks, each of which corresponds to one pedestrian, consult the description and predict future trajectories. The star topology gives StarNet two advantages over conventional models. First, StarNet is able to consider the collective influence among all pedestrians in the hub network, making more accurate predictions. Second, StarNet is computationally efficient since the number of host network is linear to the number of pedestrians. Experiments on multiple public datasets demonstrate that StarNet outperforms multiple state-of-the-arts by a large margin in terms of both accuracy and efficiency.