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 7 of 7 for “"Sim2Real Transfer"”.
-
VIEW-INVARIANT ACTION RECOGNITION IN DYNAMIC SCENES VIA SIM2REAL TRANSFER
Learning view-invariant representation is essential to improving feature extraction for action recognition. Existing approaches cannot effectively capture details for human actions due to fast-paced gameplay and implicit view- dependent representation. In this paper, it goes beyond recognizing …
-
Pedestrian Data Generation Through Simulation, Diffusion, and Conditional Image Synthesis
… creating a dataset synthetically introduces the sim2real gap where models trained on this data do not perform well when transferred to the real world. To fix this, sim2real transfer has been proposed in many works which transforms the simulated data to match its real-world counterparts. As such, …
-
Objects and Actions: Learning Representations for Open-World Robotics
… synthetic dataset, M2T2 achieves zero-shot sim2real transfer on real robots, surpassing state-of-the-art models in both overall performance and in challenging tasks requiring object re-orientation. Finally, I introduce RoboPoint, a vision-language model that predicts keypoint affordances …
-
Discovering knowledge abstractions for sample efficient embodied transfer learning
… potential on robotic applications including sim2real transfer (Chapter 3) and generalisation using a human-robot command interface (Chapter 4). We continue by developing novel unsupervised knowledge abstraction, transfer learning, methods for sample-efficient adaptation to unseen domains …
-
Sim2Robot: Training Robots for the Real-World with Imperfect Simulators
… necessary for generalization. We present 1) Sim2Real Correlation Coefficient for measuring and optimizing performance correlation between simulation and reality, enabling confident evaluation. 2) Bi-directional Domain Adaptation (BDA), and Kinematic-to-Dynamic Transfer (Kin2Dyn), …
-
Bayesian State Tracking and Sim-to-Real Transfer for Vision-and-Language Navigation
… the implications of this work for robotics, we transfer a VLN agent trained in simulation to a physical robot. To bridge the gap between the high-level discrete action space learned by the VLN agent, and the robot's low-level continuous action space, we propose a subgoal model to identify nearby …
-
Modeling Humans at Rest with Applications to Robot Assistance
… shape from a pressure image, and show that it transfers well to real world data. We also present a model that infers pose, shape and contact pressure from a depth image facing the person in bed, and it does so in the presence of blankets. This model similarly benefits from synthetic data, which …