Summary of Guiding Attention in End-to-end Driving Models, by Diego Porres et al.
Guiding Attention in End-to-End Driving Models
by Diego Porres, Yi Xiao, Gabriel Villalonga, Alexandre Levy, Antonio M. López
First submitted to arxiv on: 30 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to improve the performance and interpretability of vision-based end-to-end driving models trained by imitation learning. The goal is to create affordable solutions for autonomous driving while providing explicit and intuitive activation maps that reveal the inner workings of these models during driving. To achieve this, the authors introduce a loss term during training using salient semantic maps. This method does not require the availability of these maps during testing time or modifications to the model’s architecture. The approach is evaluated using the CIL++ state-of-the-art model and the CARLA simulator with standard benchmarks, demonstrating its effectiveness in training better autonomous driving models, particularly when data and computational resources are scarce. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to teach a car to drive without actually giving it instructions. This paper figures out how to make this work by adding a special kind of “map” that helps the car understand what’s important while driving. The map doesn’t have to be perfect, which makes it useful for real-life scenarios where data might not always be accurate. The authors test their method using a state-of-the-art model and a simulator, showing that it can help improve autonomous driving performance even when resources are limited. |
