Autonomous Driving with a Deep Dual-Model Solution for Steering and Braking Control

• URL: http://arxiv.org/abs/2405.06473v1
• Date: Fri, 10 May 2024 13:39:22 GMT
• Title: Autonomous Driving with a Deep Dual-Model Solution for Steering and Braking Control
• Authors: Ana Petra Jukić, Ana Šelek, Marija Seder, Ivana Podnar Žarko,
• Abstract summary: We present a dual-model solution that uses two deep neural networks for combined braking and steering in autonomous vehicles. We modified the NVIDIA's PilotNet model using our own original network design and reduced the number of model parameters and its memory footprint by approximately 60%. When evaluated in a simulated environment, both autonomous driving systems, one using the modified PilotNet model and the other using the original PilotNet model for steering, show similar levels of autonomous driving performance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The technology of autonomous driving is currently attracting a great deal of interest in both research and industry. In this paper, we present a deep learning dual-model solution that uses two deep neural networks for combined braking and steering in autonomous vehicles. Steering control is achieved by applying the NVIDIA's PilotNet model to predict the steering wheel angle, while braking control relies on the use of MobileNet SSD. Both models rely on a single front-facing camera for image input. The MobileNet SSD model is suitable for devices with constrained resources, whereas PilotNet struggles to operate efficiently on smaller devices with limited resources. To make it suitable for such devices, we modified the PilotNet model using our own original network design and reduced the number of model parameters and its memory footprint by approximately 60%. The inference latency has also been reduced, making the model more suitable to operate on resource-constrained devices. The modified PilotNet model achieves similar loss and accuracy compared to the original PilotNet model. When evaluated in a simulated environment, both autonomous driving systems, one using the modified PilotNet model and the other using the original PilotNet model for steering, show similar levels of autonomous driving performance.

Related papers

• Neural Network Tire Force Modeling for Automated Drifting [0.2999888908665658]
  We present a neural network architecture for predicting front tire lateral force as a drop-in replacement for physics-based approaches. We deploy these models in a nonlinear model predictive controller tuned for tracking a reference drifting trajectory.
  arXiv  Detail & Related papers  (2024-07-18T17:58:01Z)
• TEDNet: Twin Encoder Decoder Neural Network for 2D Camera and LiDAR Road Detection [2.8038082486377114]
  A novel Convolutional Neural Network model is proposed for the accurate estimation of the roadway surface. Our model is based on the use of a Twin-Decoder Neural Network (TEDNet) for independent camera and LiDAR feature extraction. Bird's Eye View projections of the camera and LiDAR data are used in this model to perform semantic segmentation on whether each pixel belongs to the road surface.
  arXiv  Detail & Related papers  (2024-05-14T08:45:34Z)
• DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Driving [65.04871316921327]
  This paper introduces a new autonomous driving system that enhances the performance and reliability of autonomous driving system. DME-Driver utilizes a powerful vision language model as the decision-maker and a planning-oriented perception model as the control signal generator. By leveraging this dataset, our model achieves high-precision planning accuracy through a logical thinking process.
  arXiv  Detail & Related papers  (2024-01-08T03:06:02Z)
• A Tricycle Model to Accurately Control an Autonomous Racecar with Locked Differential [71.53284767149685]
  We present a novel formulation to model the effects of a locked differential on the lateral dynamics of an autonomous open-wheel racecar. We include a micro-steps discretization approach to accurately linearize the dynamics and produce a prediction suitable for real-time implementation.
  arXiv  Detail & Related papers  (2023-12-22T16:29:55Z)
• Partial End-to-end Reinforcement Learning for Robustness Against Modelling Error in Autonomous Racing [0.0]
  This paper addresses the issue of increasing the performance of reinforcement learning (RL) solutions for autonomous racing cars. We propose a partial end-to-end algorithm that decouples the planning and control tasks. By leveraging the robustness of a classical controller, our partial end-to-end driving algorithm exhibits better robustness towards model mismatches than standard end-to-end algorithms.
  arXiv  Detail & Related papers  (2023-12-11T14:27:10Z)
• Efficient Perception, Planning, and Control Algorithm for Vision-Based Automated Vehicles [0.0]
  This study proposes an efficient framework for the operation of vision-based automatic vehicles. The framework requires only a monocular camera and a few radars. Experiments demonstrate that the proposed autonomous driving system can be applied in current autonomous vehicles.
  arXiv  Detail & Related papers  (2022-09-15T04:51:17Z)
• COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles [54.61668577827041]
  We introduce COOPERNAUT, an end-to-end learning model that uses cross-vehicle perception for vision-based cooperative driving. Our experiments on AutoCastSim suggest that our cooperative perception driving models lead to a 40% improvement in average success rate.
  arXiv  Detail & Related papers  (2022-05-04T17:55:12Z)
• Bayesian Optimization and Deep Learning forsteering wheel angle prediction [58.720142291102135]
  This work aims to obtain an accurate model for the prediction of the steering angle in an automated driving system. BO was able to identify, within a limited number of trials, a model -- namely BOST-LSTM -- which resulted, the most accurate when compared to classical end-to-end driving models.
  arXiv  Detail & Related papers  (2021-10-22T15:25:14Z)
• Neural Network Based Model Predictive Control for an Autonomous Vehicle [3.222802562733787]
  We study learning based controllers as a replacement for model predictive controllers (MPC) for the control of autonomous vehicles. We compare training by supervised learning and by reinforcement learning. This work aims at producing controllers that can both be embedded on real-time platforms and amenable to verification by formal methods techniques.
  arXiv  Detail & Related papers  (2021-07-30T12:11:31Z)
• Efficient and Robust LiDAR-Based End-to-End Navigation [132.52661670308606]
  We present an efficient and robust LiDAR-based end-to-end navigation framework. We propose Fast-LiDARNet that is based on sparse convolution kernel optimization and hardware-aware model design. We then propose Hybrid Evidential Fusion that directly estimates the uncertainty of the prediction from only a single forward pass.
  arXiv  Detail & Related papers  (2021-05-20T17:52:37Z)
• A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN [59.57221522897815]
  We propose a neural network model based on trajectories information for driving behavior recognition. We evaluate the proposed model on the public BLVD dataset, achieving a satisfying performance.
  arXiv  Detail & Related papers  (2021-03-01T06:47:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.