Trajectory Prediction with Linguistic Representations

10/19/2021
by   Yen-Ling Kuo, et al.
9

Language allows humans to build mental models that interpret what is happening around them resulting in more accurate long-term predictions. We present a novel trajectory prediction model that uses linguistic intermediate representations to forecast trajectories, and is trained using trajectory samples with partially annotated captions. The model learns the meaning of each of the words without direct per-word supervision. At inference time, it generates a linguistic description of trajectories which captures maneuvers and interactions over an extended time interval. This generated description is used to refine predictions of the trajectories of multiple agents. We train and validate our model on the Argoverse dataset, and demonstrate improved accuracy results in trajectory prediction. In addition, our model is more interpretable: it presents part of its reasoning in plain language as captions, which can aid model development and can aid in building confidence in the model before deploying it.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/18/2022

ScePT: Scene-consistent, Policy-based Trajectory Predictions for Planning

Trajectory prediction is a critical functionality of autonomous systems ...
research
06/27/2022

Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with Relational Reasoning

Demystifying the interactions among multiple agents from their past traj...
research
10/18/2020

Multiple Future Prediction Leveraging Synthetic Trajectories

Trajectory prediction is an important task, especially in autonomous dri...
research
06/01/2021

Enhancing Trajectory Prediction using Sparse Outputs: Application to Team Sports

Sophisticated trajectory prediction models that effectively mimic team d...
research
04/09/2016

Towards an Indexical Model of Situated Language Comprehension for Cognitive Agents in Physical Worlds

We propose a computational model of situated language comprehension base...
research
04/11/2023

Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrums

With the fast development of AI-related techniques, the applications of ...
research
07/31/2019

DROGON: A Causal Reasoning Framework for Future Trajectory Forecast

We propose DROGON (Deep RObust Goal-Oriented trajectory prediction Netwo...

Please sign up or login with your details

Forgot password? Click here to reset