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 40 for “"Domain randomization"”.
-
Lossy Light Field Compression Using Modern Deep Learning and Domain Randomization Techniques
… with varying viewpoints, known as light fields. Domain Randomization is explored in detail, and used to generate the largest light field dataset we are aware of, to be used as training data. We formulate the task of compression under the frameworks of neural networks and calculate a quantization …
-
Transferrable learning from synthetic data: novel texture synthesis using Domain Randomization for visual scene understanding
… computer vision and robotics systems. Due to domain shift, models trained on synthetic data typically underperform those trained on real-world data when deployed in the real world. Domain Randomization is a data generation approach for the synthesis of artificial data. The Domain Randomization …
-
Application of reinforcement learning methods for line following with an autonomous robot /
… (RL) methods for the line-following task using domain randomization techniques to transfer a trained policy from a simulated environment to a physical TurtleBot Burger robot. A simulation environment based on the PyBullet physics engine and the Gymnasium library was adapted for the TurtleBot …
-
Domain Adaptation for Autonomous Driving
Metric based method is a promising approach to domain adaptation, which aims to align the marginal distribution of different domains with a similar conditional distribution. The thesis explores applying domain adaptation for autonomous driving and proposes domain adaptation methods for 2D image …
-
Robust reinforcement learning with intrinsic stochasticity in real-time simulation
… These solutions include system identification, domain adaptation, and domain randomization. While these methods succeed in creating more robust agents, they are highly extensive, heuristic, and require expert knowledge to implement them. In this work, we propose a method based on the principles …
-
Synthetic Imagery Data Generation for Training and Testing Deep Learning Models of Object Recognition
… of design strategies: i) image stylization, ii) domain randomization and iii) meta learning.My first set of work focuses on utilization of synthetic data generated from image stylization methods for testing of autonomous driving perception systems. Autonomous driving perception systems require …
-
Deep Reinforcement Learning for Multirotor Flight Control: A Comparative Study of Sim-to-Real Training and Real-World Performance
… ablation studies evaluated the effects of domain randomization, reward weighting, observation representation, and neural network architecture. Policies were trained in a MuJoCo-based simulator and deployed via TensorFlow Lite Micro inference on PX4 flight controllers. Domain randomization …
-
MORP: Monocular Orientation Regression Pipeline
… synthetic images using the Unity game engine and domain randomization. Our deep learning model, trained exclusively on these synthetic images, demonstrates promising results in estimating the orientations of common objects. Notably, our model achieves a median geodesic distance error of 3.9 …
-
Adaptive Policy Optimization via Meta-Learning in Deeptop for Restless Multi-Arm Bandits
… shared policy network that is trained with domain randomization to learn a universal threshold rule. This structured design allows EADeepTOP to achieve successful generalization and zero-shot adaptation in AoI-driven Restless Multi-Armed Bandit settings. Furthermore, it significantly reduces …
-
Deep learning under data scarcity in science and engineering applications
… in vision-language models (VLMs). In the AFM domain, we develop a few-shot learning framework to efficiently characterize force-distance curves, surpassing manual analysis speed and matching human accuracy. Additionally, we utilize data processing techniques to improve AFM data quality and …
-
Multi-Agent Hierarchical Distributed NMPC With Learned Locomotion via Reinforcement Learning
… Proximal Policy Optimization (PPO) with targeted domain randomization, the actor-critic policy directly maps proprioceptive observations to joint position targets. The mathematical formulation of the ADMM-NMPC planner and the underlying RL reward structures are detailed, and the integrated …
-
Capture of Free-Floating Targets Using End-to-End Reinforcement Learning: Theoretical Foundations and Ground Demonstrations
… developed using the PyBullet physics engine with domain randomization to train and evaluate DRL agents under realistic dynamics. The agents use hierarchical control strategies, combining curriculum-based learning for path planning and tactile sensor feedback for force regulation to minimize …
-
Deep Reinforcement Learning Framework for Autonomous Surface Vehicles in Environmental Cleanup
… By integrating system identification with domain randomization, we reduce the sim-to-real gap, enhancing the robustness and energy efficiency of the trained agents. The proposed approach is validated through simulation and real-world experiments, demonstrating improved task completion times …
-
Multistream Gaze Estimation with Anatomical Eye Region Isolation by Synthetic to Real Transfer Learning
… network is then transferred to the real domain for generating masks for the real-world eye images. In order to successfully make the transfer, we exploit domain randomization in the training process, which allows for the synthetic images to benefit from a larger variance with the help of …
-
Domain Invariant and Semantic Aware Visual Servoing
… policies in low cost and safe manner. We propose domain invariant visual servoing for both manipulation and navigation that enables seamless and direct transfer of vision-based robot policies from simulation to the real world. By introducing simulation randomization (domain randomization) we make …
-
On Safety in Sequential Decision Learning
… operating in gusty wind conditions. Using domain randomization and disturbance estimation techniques, we create a learning-based controller that successfully transfers from simulation to real-world flight, demonstrating superior wind rejection capabilities compared to traditional control …
-
Deep-Reinforcement Learning Agents in Autonomous Directional Drilling and Geosteering
… learning in uncertain drilling environments. Domain randomization further enhanced generalization, allowing agents to adapt to new geologies and successfully steer even when initial well plans were inaccurate. Second, the framework was extended to incorporate geological and operational …
-
Deep-Reinforcement Learning Agents in Autonomous Directional Drilling and Geosteering
… learning in uncertain drilling environments. Domain randomization further enhanced generalization, allowing agents to adapt to new geologies and successfully steer even when initial well plans were inaccurate. Second, the framework was extended to incorporate geological and operational …
-
Deep-Reinforcement Learning Agents in Autonomous Directional Drilling and Geosteering
… learning in uncertain drilling environments. Domain randomization further enhanced generalization, allowing agents to adapt to new geologies and successfully steer even when initial well plans were inaccurate. Second, the framework was extended to incorporate geological and operational …
-
Deep-Reinforcement Learning Agents in Autonomous Directional Drilling and Geosteering
… learning in uncertain drilling environments. Domain randomization further enhanced generalization, allowing agents to adapt to new geologies and successfully steer even when initial well plans were inaccurate. Second, the framework was extended to incorporate geological and operational …
Page 1 of 2