# Efficient Latent Representations using Multiple Tasks for Autonomous Driving

arXiv: https://arxiv.org/abs/2003.00695 · HTML: https://mlsanity.com/paper/2003.00695/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2020.

## Built on by (most cited first, 1 of 1)

- [Towards Learning Generalizable Driving Policies from Restricted Latent Representations](https://mlsanity.com/paper/2111.03688/) (2021)

## Abstract (arXiv)

Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level representations that encode a vehicle's environment as images have become a popular choice, but they are quite high-dimensional, which limits their use in data-scarce cases such as reinforcement learning. In this article, we propose to learn a low dimensional and rich feature representation of the environment by training an encoder-decoder deep neural network to predict multiple application relevant factors such as trajectories of other agents. We demonstrate that the use of the multi-head encoder-decoder neural network results in a more informative representation compared to a single-head encoder-decoder model. In particular, the proposed representation learning approach helps the policy network to learn faster, with increased performance and with less data, compared to existing approaches using a single-head network.