Benchmarking Domain Randomisation for Visual Sim-to-Real Transfer
Domain randomisation is a very popular method for visual sim-to-real transfer in robotics, due to its simplicity and ability to achieve transfer without any real-world images at all. Nonetheless, a number of design choices must be made to achieve optimal transfer. In this paper, we perform a comprehensive benchmarking study on these different choices, with two key experiments evaluated on a real-world object pose estimation task. First, we study the rendering quality, and find that a small number of high-quality images is superior to a large number of low-quality images. Second, we study the type of randomisation, and find that both distractors and textures are important for generalisation to novel environments.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingPose EstimationSimilar Papers 제목 키워드 기반
BehAVE: Behaviour Alignment of Video Game Encodings
Domain randomisation enhances the transferability of vision models across visually distinct domains with similar content. However, current methods heavily depend on intricate simulation engines, hampering feasibility and…
DiversityFPS GamesVideo UnderstandingAnalysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
Deep reinforcement learning has the potential to train robots to perform complex tasks in the real world without requiring accurate models of the robot or its environment. A practical approach is to train agents in simul…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer
Model-based RL is a promising approach for real-world robotics due to its improved sample efficiency and generalization capabilities compared to model-free RL. However, effective model-based RL solutions for vision-based…
CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning
Distributed reinforcement learning policies face network delays, jitter, and packet loss when deployed across edge devices and cloud servers. Standard RL training assumes zero-latency interaction, causing severe performa…
Reinforcement LearningAttention-Privileged Reinforcement Learning
Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space). Visual domain randomisation …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)