# PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings

## TL;DR

This paper introduces a probabilistic model for predicting future multi-agent interactions in autonomous driving, capable of standard and goal-conditioned forecasting, improving accuracy over existing methods.

## Contribution

It presents a novel probabilistic framework for both standard and goal-conditioned multi-agent trajectory forecasting in autonomous driving scenarios.

## Key findings

- Model outperforms state-of-the-art in multi-agent trajectory prediction.
- Conditional forecasting improves prediction accuracy when conditioned on the AV's goal.
- Model effectively captures interactions among multiple agents in complex scenarios.

## Abstract

For autonomous vehicles (AVs) to behave appropriately on roads populated by human-driven vehicles, they must be able to reason about the uncertain intentions and decisions of other drivers from rich perceptual information. Towards these capabilities, we present a probabilistic forecasting model of future interactions between a variable number of agents. We perform both standard forecasting and the novel task of conditional forecasting, which reasons about how all agents will likely respond to the goal of a controlled agent (here, the AV). We train models on real and simulated data to forecast vehicle trajectories given past positions and LIDAR. Our evaluation shows that our model is substantially more accurate in multi-agent driving scenarios compared to existing state-of-the-art. Beyond its general ability to perform conditional forecasting queries, we show that our model's predictions of all agents improve when conditioned on knowledge of the AV's goal, further illustrating its capability to model agent interactions.