PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings
Citations Over TimeTop 10% of 2019 papers
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.
Related Papers
- → Social LSTM: Human Trajectory Prediction in Crowded Spaces(2016)3,401 cited
- → Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks(2019)663 cited
- → r2p2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting(2018)234 cited
- → IntentNet: Learning to Predict Intention from Raw Sensor Data(2021)250 cited
- → MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction(2019)137 cited