Summary of Autonomous Driving with Perception Uncertainties: Deep-ensemble Based Adaptive Cruise Control, by Xiao Li et al.
Autonomous Driving With Perception Uncertainties: Deep-Ensemble Based Adaptive Cruise Control
by Xiao Li, H. Eric Tseng, Anouck Girard, Ilya Kolmanovsky
First submitted to arxiv on: 22 Mar 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Robotics (cs.RO); Systems and Control (eess.SY)
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 The paper proposes an Ensemble of Deep Neural Network regressors (Deep Ensemble) that generates predictions with quantified uncertainties, addressing the limitations of black-box DNNs in autonomous driving perception systems. Specifically, it develops an Adaptive Cruise Control (ACC) algorithm using Stochastic Model Predictive Control (MPC) and chance constraints to provide a probabilistic safety guarantee. The Deep Ensemble is employed to estimate distance headway from RGB images, enabling the controller to account for estimation uncertainty. The ACC algorithm is evaluated on high-fidelity traffic simulators and real-world datasets, demonstrating effective speed tracking and car following while maintaining safe distances. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps create safer autonomous vehicles by improving perception systems. It uses special kinds of artificial intelligence (AI) called Deep Neural Networks to understand the environment around a self-driving car. But these AI models can be tricky to use because they don’t always explain why they made certain decisions. To solve this problem, the researchers created an “ensemble” of many AI models that work together and give uncertainty estimates about their predictions. This helps the car’s controller make more informed decisions and ensures a safe distance from other vehicles. The team tested its approach in simulated traffic scenarios and found it worked well. |
Keywords
» Artificial intelligence » Neural network » Tracking
