Scene Induced Multi-Modal Trajectory Forecasting via Planning

05/23/2019
by   Nachiket Deo, et al.
0

We address multi-modal trajectory forecasting of agents in unknown scenes by formulating it as a planning problem. We present an approach consisting of three models; a goal prediction model to identify potential goals of the agent, an inverse reinforcement learning model to plan optimal paths to each goal, and a trajectory generator to obtain future trajectories along the planned paths. Analysis of predictions on the Stanford drone dataset, shows generalizability of our approach to novel scenes.

READ FULL TEXT

page 1

page 2

research
01/03/2020

Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans

In this paper, we address the problem of forecasting agent trajectories ...
research
12/02/2020

From Goals, Waypoints Paths To Long Term Human Trajectory Forecasting

Human trajectory forecasting is an inherently multi-modal problem. Uncer...
research
03/31/2022

End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps

In this paper, we aim to forecast a future trajectory distribution of a ...
research
10/02/2020

Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation

In this paper, we present Goal-GAN, an interpretable and end-to-end trai...
research
12/13/2019

The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

This paper studies the problem of predicting the distribution over multi...
research
04/17/2023

Pretrained Language Models as Visual Planners for Human Assistance

To make progress towards multi-modal AI assistants which can guide users...
research
12/22/2016

First-Person Activity Forecasting with Online Inverse Reinforcement Learning

We address the problem of incrementally modeling and forecasting long-te...

Please sign up or login with your details

Forgot password? Click here to reset