Making accurate motion prediction of the surrounding traffic agents such as pedestrians, vehicles, and cyclists is crucial for autonomous driving. Recent data-driven motion prediction methods have attempted to learn to directly regress the exact future position or its distribution from massive amount of trajectory data. However, it remains difficult for these methods to provide multimodal predictions as well as integrate physical constraints such as traffic rules and movable areas. In this work we propose a novel two-stage motion prediction framework, Trajectory Proposal Network (TPNet). TPNet first generates a candidate set of future trajectories as hypothesis proposals, then makes the final predictions by classifying and refining the proposals which meets the physical constraints. By steering the proposal generation process, safe and multimodal predictions are realized. Thus this framework effectively mitigates the complexity of motion prediction problem while ensuring the multimodal output. Experiments on four large-scale trajectory prediction datasets, i.e. the ETH, UCY, Apollo and Argoverse datasets, show that TPNet achieves the state-of-the-art results both quantitatively and qualitatively.
Post-interactive Multimodal Trajectory Prediction for Autonomous Driving
College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机与通信工程学院）；College of Mechanical and Vehicle Engineering, Hunan University（湖南大学机械与运载工程学院）；Department of Computer Science, The University of Hong Kong（香港大学计算机科学系）；Department of Civil Engineering, Monash University（莫纳什大学土木工程系）
BEVTraj: Map-Free End-to-End Trajectory Prediction in Bird's-Eye View with Deformable Attention and Sparse Goal Proposals
Department of Automobile and IT Convergence, Kookmin University（汽车与IT融合系，韩国釜山大学）；Department of Automotive Engineering, Kookmin University（汽车工程系，韩国釜山大学）；Graduate School of Automobile and Mobility, Kookmin University（汽车与移动研究生院，韩国釜山大学）
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；MORAI Inc.（MORAI公司）；Hanyang University（汉阳大学）
Prior arts in the field of motion predictions for autonomous driving tend to focus on finding a trajectory that is close to the ground truth trajectory. Such problem formulations and approaches, however, frequently lead to 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 loss function, \textit{Lane Loss}, that ensures map-adaptive diversity and accommodates geometric constraints. A two-stage tra…
Fine-Grained Behavior and Lane Constraints Guided Trajectory Prediction Method
School of Mechanical Engineering, Zhejiang University（浙江大学机械工程学院）；Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology, School of Automation and Intelligent Manufacturing, Southern University of Science and Technology（南方科技大学自动化与智能制造学院广东省全驱系统控制理论与技术重点实验室）；Leapmotor Technology（零跑科技）
MGTraj: Multi-Granularity Goal-Guided Human Trajectory Prediction with Recursive Refinement Network
Division of Emerging Interdisciplinary Areas, The Hong Kong University of Science and Technology（新兴交叉领域分校，香港科学与技术大学）；Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou)（机器人与自主系统方向，香港科学与技术大学（广州））
AImageLab（AImage实验室）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Understanding human motion behaviour is a critical task for several possible applications like self-driving cars or social robots, and in general for all those settings where an autonomous agent has to navigate inside a human-centric environment. This is non-trivial because human motion is inherently multi-modal: given a history of human motion paths, there are many plausible ways by which people could move in the future. Additionally, people activities are often driven by goals, e.g. reaching particular locations or interacting with the environment. We address the aforementioned aspects by pr…
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）；University of Heidelberg（海德堡大学）；TCS Research and Innovation Labs（塔塔咨询服务研究与创新实验室）
Autonomous explorative robots frequently encounter scenarios where multiple future trajectories can be pursued. Often these are cases with multiple paths around an obstacle or trajectory options towards various frontiers. Humans in such situations can inherently perceive and reason about the surrounding environment to identify several possibilities of either manoeuvring around the obstacles or moving towards various frontiers. In this work, we propose a 2 stage Convolutional Neural Network architecture which mimics such an ability to map the perceived surroundings to multiple trajectories that…
MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Xiaomi EV（小米汽车）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学智能产业研究院）
Knowledge-Informed Multi-Agent Trajectory Prediction at Signalized Intersections for Infrastructure-to-Everything
College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Shanghai Institute of Intelligent Science and Technology, Tongji University（同济大学上海智能科学与技术研究院）；Department of Electrical and Computer Engineering, Technical University of Munich（慕尼黑技术大学电子与计算机工程系）
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. However, it is not trivial to solve the data-association problem in an end-to-end fashion. In this paper, we propose a novel proposal-based learnable framework, which models MOT as a proposal generation, proposal scoring and trajectory inference paradigm on an affinity graph. This framework is similar to the two-stage object detector Faster RCNN, and can solve the MOT problem in a data-driven way. For proposal generation, we propose an iterative graph clustering met…
Stanford University（斯坦福大学）；Tencent AI Lab（腾讯人工智能实验室）
Perceiving and manipulating 3D articulated objects (e.g., cabinets, doors) in human environments is an important yet challenging task for future home-assistant robots. The space of 3D articulated objects is exceptionally rich in their myriad semantic categories, diverse shape geometry, and complicated part functionality. Previous works mostly abstract kinematic structure with estimated joint parameters and part poses as the visual representations for manipulating 3D articulated objects. In this paper, we propose object-centric actionable visual priors as a novel perception-interaction handshak…
CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
Department of Automation, University of Science and Technology of China（中国科学技术大学自动化系）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；School of Electronic Information Engineering, Beihang University（北航电子信息技术学院）；National College for Excellent Engineers, Beihang University（北航卓越工程师学院）
Stanford University（斯坦福大学）；SLAC National Accelerator Laboratory（SLAC国家加速器实验室）
Liquid Argon Time Projection Chambers (LArTPCs) are high resolution particle imaging detectors, employed by accelerator-based neutrino oscillation experiments for high precision physics measurements. While images of particle trajectories are intuitive to analyze for physicists, the development of a high quality, automated data reconstruction chain remains challenging. One of the most critical reconstruction steps is particle clustering: the task of grouping 3D image pixels into different particle instances that share the same particle type. In this paper, we propose the first scalable deep lea…
UC Berkeley（加州大学伯克利分校）；UC San Diego（加州大学圣迭戈分校）；CMU（卡内基梅隆大学）
Learning long-term dynamics models is the key to understanding physical common sense. Most existing approaches on learning dynamics from visual input sidestep long-term predictions by resorting to rapid re-planning with short-term models. This not only requires such models to be super accurate but also limits them only to tasks where an agent can continuously obtain feedback and take action at each step until completion. In this paper, we aim to leverage the ideas from success stories in visual recognition tasks to build object representations that can capture inter-object and object-environme…
Accurate and robust trajectory prediction of neighboring agents is critical for autonomous vehicles traversing in complex scenes. Most methods proposed in recent years are deep learning-based due to their strength in encoding complex interactions. However, unplausible predictions are often generated since they rely heavily on past observations and cannot effectively capture the transient and contingency interactions from sparse samples. In this paper, we propose a hierarchical hybrid framework of deep learning (DL) and reinforcement learning (RL) for multi-agent trajectory prediction, to cope …
LTMSformer: A Local Trend-Aware Attention and Motion State Encoding Transformer for Multi-Agent Trajectory Prediction
College of Mechanical and Vehicle Engineering, Hunan University（湖南大学机械与车辆工程学院）；School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）
