Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 29 for “"CARLA simulator"”.

  1. A PASSENGER-CENTRIC AUTONOMOUS DRIVING SOLUTION VALIDATED THROUGH VIRTUAL REALITY

    … at a lower cost. The proposed platform utilizes CARLA simulator to create immersive and realistic VR experiences for testing CAV behaviors. This platform also addresses the need for high-quality and royalty-free datasets, which will benefit research communities with limited funding resources.

    cornell Repository record for A PASSENGER-CENTRIC AUTONOMOUS DRIVING SOLUTION VALIDATED THROUGH VIRTUAL REALITY (opens in a new tab)

  2. IoT Architecture for Enhancing Wayfinding and Accessibility in Smart Cities

    … as a transformative solution. Simulations in the CARLA Simulator evaluated AWayNet across varied urban scenarios, revealing a need for only 8 individuals per city block for stable network functionality. When equipped with AWayNet, route completion times improved by 1.2x for well-sighted users and …

    usf Repository record for IoT Architecture for Enhancing Wayfinding and Accessibility in Smart Cities (opens in a new tab)

  3. Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving

    … driving together. The system was evaluated using CARLA Simulator, focusing on CARLA Leaderboard metrics. Despite the lack of overall improvement over the base CNN model, the system showed some positive results, particularly in reducing red light infractions and wrong turns, suggesting that the …

    tamu Repository record for Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving (opens in a new tab)

  4. Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving

    … driving together. The system was evaluated using CARLA Simulator, focusing on CARLA Leaderboard metrics. Despite the lack of overall improvement over the base CNN model, the system showed some positive results, particularly in reducing red light infractions and wrong turns, suggesting that the …

    tamu Repository record for Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving (opens in a new tab)

  5. Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving

    … driving together. The system was evaluated using CARLA Simulator, focusing on CARLA Leaderboard metrics. Despite the lack of overall improvement over the base CNN model, the system showed some positive results, particularly in reducing red light infractions and wrong turns, suggesting that the …

    tamu Repository record for Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving (opens in a new tab)

  6. Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving

    … driving together. The system was evaluated using CARLA Simulator, focusing on CARLA Leaderboard metrics. Despite the lack of overall improvement over the base CNN model, the system showed some positive results, particularly in reducing red light infractions and wrong turns, suggesting that the …

    tamu Repository record for Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving (opens in a new tab)

  7. Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving

    … driving together. The system was evaluated using CARLA Simulator, focusing on CARLA Leaderboard metrics. Despite the lack of overall improvement over the base CNN model, the system showed some positive results, particularly in reducing red light infractions and wrong turns, suggesting that the …

    tamu Repository record for Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving (opens in a new tab)

  8. Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving

    … driving together. The system was evaluated using CARLA Simulator, focusing on CARLA Leaderboard metrics. Despite the lack of overall improvement over the base CNN model, the system showed some positive results, particularly in reducing red light infractions and wrong turns, suggesting that the …

    tamu Repository record for Assessing Vision-Language Model Correction and Confirmation in End-to-End Imitation Learning for Autonomous Driving (opens in a new tab)

  9. Towards Verified Vision-Based Neural Network Controllers for Autonomous Lane-Following

    … stronger safety guarantees. Experiments in the CARLA simulator demonstrate that our approaches can effectively verify the safety properties of vision-based controllers across various driving scenarios, while maintaining performance in lane-following tasks. The results demonstrate that our …

    wustl Repository record for Towards Verified Vision-Based Neural Network Controllers for Autonomous Lane-Following (opens in a new tab)

  10. LiDAR Based Object Detection and Tracking in Stationary Applications

    … traffic on a highway are developed in the CARLA simulator to further validate tracking performance.

    tamu Repository record for LiDAR Based Object Detection and Tracking in Stationary Applications (opens in a new tab)

  11. DriveMind: a vision-based end-to-end autonomous defensive driver

    … This work makes extensive use of the CARLA simulator for all data, experiments, benchmarking and tests, making it a closed-loop scenario. Results from the experiments show that there is a considerable increase in the safety of the model “DriveTransformer”. This shows that defensive …

    bu Repository record for DriveMind: a vision-based end-to-end autonomous defensive driver (opens in a new tab)

  12. Utilizing Human Feedback in the Soft Actor-Critic Algorithm for Autonomous Driving

    … task in OpenAI gym and autonomous driving in the CARLA simulator. The results showed a considerable reduction in the training time and a significant increase in gaining rewards for human demonstration and Online Virtual training compared to the baseline SAC. The proposed approach is expected to be …

    tamu Repository record for Utilizing Human Feedback in the Soft Actor-Critic Algorithm for Autonomous Driving (opens in a new tab)

  13. ROUGH TERRAIN AUTONOMOUS GROUND VEHICLE SIMULATION: CARLA SIMULATION AND DEEP LEARNING BASED PREDICTIVE MODEL

    … and customizable rough terrain on RoadRunner and CARLA simulation. The first contribution of this thesis is the method to customize arbitrary rough terrain maps on RoadRunner and simulate various vehicles driving on that customized map in CARLA simulator with real-time data collection and dataset …

    jhu Repository record for ROUGH TERRAIN AUTONOMOUS GROUND VEHICLE SIMULATION: CARLA SIMULATION AND DEEP LEARNING BASED PREDICTIVE MODEL (opens in a new tab)

  14. An empirical study of the effect of variable network performance on teleoperated driving

    … remote driver’s experience. Utilising the TELECARLA simulator, a network-aware extension of the CARLA simulator, this thesis emulates network impairments and analyses their impact on driver performance. Key performance metrics, including Time to Collision (TTC), Steering Wheel Reversal Rate …

    cork Repository record for An empirical study of the effect of variable network performance on teleoperated driving (opens in a new tab) Embargoed until 2031-12-31

  15. Adversarial Robustness of Modular Autonomous Driving Agents for Lane Keeping

    … modular deep learning lane-keeping agent in the CARLA simulator, consisting of a learned lane detection module followed by a learned steering angle predictor that consumes RGB and lane-mask inputs. We evaluate white-box, digital, ℓ∞-bounded evasion attacks using Fast Gradient Sign Method (FGSM) …

    waterloo Repository record for Adversarial Robustness of Modular Autonomous Driving Agents for Lane Keeping (opens in a new tab)

  16. Integrating a Neuro-Symbolic Planner for Safe Driving

    … developed in Scenic and executed in the CARLA simulator, with its performance compared against an end-to-end deep-learning-based planner using the same set of 144 scenarios. The results demonstrate that this modular neuro-symbolic approach achieves a higher rate of safe, goal-reaching …

    chalmers Repository record for Integrating a Neuro-Symbolic Planner for Safe Driving (opens in a new tab)

  17. Adapting to unseen driving conditions using context-aware neural networks

    … during evaluation. The approach is tested in the CARLA simulator wherein the torque and steering curves of a vehicle are modified during training and evaluation. Furthermore the agent is trained only on a track with a relatively large radius of curvature but is evaluated on a track with much …

    texas Repository record for Adapting to unseen driving conditions using context-aware neural networks (opens in a new tab)

  18. Multiple Target Tracking Using Random Finite Sets

    … on KITTI dataset and simulated data from CARLA simulator. The CMM-LMB filter leads to a lower OSPA error metric than the Multiple Model LMB and LMB filters in both cases. The second half looks into sensor management for MTT using a sensor with a narrow field of view and a finite action …

    umn Repository record for Multiple Target Tracking Using Random Finite Sets (opens in a new tab)

  19. On the role of explainability and uncertainty in ensuring safety of AI applications

    … (BNN) controller trained on data from the Carla simulator. BNNs have the ability to capture the uncertainty within the learning model, while retaining the main advantages intrinsic to neural networks. We propose two methods to evaluate the safety of decisions of BNN controllers in the …

    oxford Repository record for On the role of explainability and uncertainty in ensuring safety of AI applications (opens in a new tab)

Page 1 of 2