Conditional Generative Neural System for Probabilistic Trajectory Prediction

5 May 2019 Jiachen Li Hengbo Ma Masayoshi Tomizuka

Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are critical for intelligent systems such as autonomous vehicles and wheeled mobile robotics navigating in complex scenarios to achieve safe and high-quality decision making, motion planning and control. Due to the uncertain nature of the future, it is desired to make inference from a probability perspective instead of deterministic prediction... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Trajectory Prediction ETH/UCY CGNS ADE-8/12 0.49 # 6
Trajectory Prediction Stanford Drone CGNS ADE-8/12 @K = 20 15.6 # 7
FDE-8/12 @K= 20 28.2 # 7

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet