MultiXNet: Multiclass Multistage Multimodal Motion Prediction
원문 초록
One of the critical pieces of the self-driving puzzle is understanding the surroundings of a self-driving vehicle (SDV) and predicting how these surroundings will change in the near future. To address this task we propose MultiXNet, an end-to-end approach for detection and motion prediction based directly on lidar sensor data. This approach builds on prior work by handling multiple classes of traffic actors, adding a jointly trained second-stage trajectory refinement step, and producing a multimodal probability distribution over future actor motion that includes both multiple discrete traffic behaviors and calibrated continuous position uncertainties. The method was evaluated on large-scale, real-world data collected by a fleet of SDVs in several cities, with the results indicating that it outperforms existing state-of-the-art approaches.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Autoregression-free video prediction using diffusion model for mitigating error propagation
TrajFlow: Multi-modal Motion Prediction via Flow Matching
Position Dependent Prediction Combination For Intra-Frame Video Coding
UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction
Open-World Social Event Classification
EasySpider: A No-Code Visual System for Crawling the Web
토론
이 논문과 연결된 포럼 글이 아직 없습니다.