Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In this paper, we present a domain-invariant representation learning (DIRL) algorithm to adapt deep models to the physical environment with a small amount of real data. Existing approaches that only mitigate the covariate shift by aligning the marginal distributions across the domains and assume the conditional distributions to be domain-invariant can lead to ambiguous transfer in real scenarios. We propose to jointly align the marginal (input domains) and the conditional (output labels) distributions to mitigate the covariate and the conditional shift across the domains with adversarial learning, and combine it with a triplet distribution loss to make the conditional distributions disjoint in the shared feature space. Experiments on digit domains yield state-of-the-art performance on challenging benchmarks, while sim-to-real transfer of object recognition for vision-based decluttering with a mobile robot improves from 26.8 % to 91.0 %, resulting in 86.5 % grasping accuracy of a wide variety of objects. Code and supplementary details are available at https://sites.google.com/view/dirl
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 t…
We propose a method to predict the sim-to-real transfer performance of RL policies. Our transfer metric simplifies the selection of training setups (such as algorithm, hyperparameters, randomizations) and policies in simulation, without the need for extensive and time-consuming real-world rollouts. A probabilistic dynamics model is trained alongside the policy and evaluated on a fixed set of real-world trajectories to obtain the transfer metric. Experiments show that the transfer metric is highly correlated with policy performance in both simulated and real-world robotic environments for compl…
GeCo-SRT: Geometry-aware Continual Adaptation for Robotic Cross-Task Sim-to-Real Transfer
Beijing Forestry University（北京林业大学）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）；Beijing Key Laboratory of Research on Large Models and Intelligent Governance（北京大型模型与智能治理研究重点实验室）；Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（下一代智能搜索与推荐工程研究中心，教育部）
Technische Universität München（慕尼黑工业大学）；Agile Robots AG（敏捷机器人公司）；Universität Hamburg（汉堡大学）
Recently, deep reinforcement learning (RL) has shown some impressive successes in robotic manipulation applications. However, training robots in the real world is nontrivial owing to sample efficiency and safety concerns. Sim-to-real transfer is proposed to address the aforementioned concerns but introduces a new issue called the reality gap. In this work, we introduce a sim-to-real learning framework for vision-based assembly tasks and perform training in a simulated environment by employing inputs from a single camera to address the aforementioned issues. We present a domain adaptation metho…
Politecnico di Torino（都灵理工大学）；Aalto University（阿尔托大学）
In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation; however, finding optimal randomization distributions can be difficult. In this paper, we introduce DROPO, a novel method for estimating domain randomization distributions for safe sim-to-real transfer. Unlike prior work, DROPO only requires a limited, precollected offline dataset of trajectories, and explicitly models parameter uncertainty to match real data using a likelihood-based approach. We demonstrate …
Toyota Technological Institute at Chicago（芝加哥丰田理工学院）；McGill University（麦吉尔大学）
This work provides a complete framework for the simulation, co-optimization, and sim-to-real transfer of the design and control of soft legged robots. The compliance of soft robots provides a form of "mechanical intelligence" -- the ability to passively exhibit behaviors that would otherwise be difficult to program. Exploiting this capacity requires careful consideration of the coupling between mechanical design and control. Co-optimization provides a promising means to generate sophisticated soft robots by reasoning over this coupling. However, the complex nature of soft robot dynamics makes …
Tencent Robotics X（腾讯机器人X实验室）；Imperial College London（帝国理工学院）
Reinforcement Learning (RL) methods have been widely applied for robotic manipulations via sim-to-real transfer, typically with proprioceptive and visual information. However, the incorporation of tactile sensing into RL for contact-rich tasks lacks investigation. In this paper, we model a tactile sensor in simulation and study the effects of its feedback in RL-based robotic control via a zero-shot sim-to-real approach with domain randomization. We demonstrate that learning and controlling with feedback from tactile sensor arrays at the gripper, both in simulation and reality, can enhance gras…
Simulation-to-reality transfer has emerged as a popular and highly successful method to train robotic control policies for a wide variety of tasks. However, it is often challenging to determine when policies trained in simulation are ready to be transferred to the physical world. Deploying policies that have been trained with very little simulation data can result in unreliable and dangerous behaviors on physical hardware. On the other hand, excessive training in simulation can cause policies to overfit to the visual appearance and dynamics of the simulator. In this work, we study strategies t…
This paper presents a novel method for transferring motion planning and control policies between a teacher and a learner robot. With this work, we propose to reduce the sim-to-real gap, transfer knowledge designed for a specific system into a different robot, and compensate for system aging and failures. To solve this problem we introduce a Schwarz-Christoffel mapping-based method to geometrically stretch and fit the control inputs from the teacher into the learner command space. We also propose a method based on primitive motion generation to create motion plans and control inputs compatible …
Despite recent advances in Reinforcement Learning (RL), many problems, especially real-world tasks, remain prohibitively expensive to learn. To address this issue, several lines of research have explored how tasks, or data samples themselves, can be sequenced into a curriculum to learn a problem that may otherwise be too difficult to learn from scratch. However, generating and optimizing a curriculum in a realistic scenario still requires extensive interactions with the environment. To address this challenge, we formulate the curriculum transfer problem, in which the schema of a curriculum opt…
Zero-shot sim-to-real transfer of tasks with complex dynamics is a highly challenging and unsolved problem. A number of solutions have been proposed in recent years, but we have found that many works do not present a thorough evaluation in the real world, or underplay the significant engineering effort and task-specific fine tuning that is required to achieve the published results. In this paper, we dive deeper into the sim-to-real transfer challenge, investigate why this is such a difficult problem, and present objective evaluations of a number of transfer methods across a range of real-world…
In this work we show how to use the Operational Space Control framework (OSC) under joint and cartesian constraints for reinforcement learning in cartesian space. Our method is therefore able to learn fast and with adjustable degrees of freedom, while we are able to transfer policies without additional dynamics randomizations on a KUKA LBR iiwa peg in-hole task. Before learning in simulation starts, we perform a system identification for aligning the simulation environment as far as possible with the dynamics of a real robot. Adding constraints to the OSC controller allows us to learn in a saf…
Recent work in Vision-and-Language Navigation (VLN) has presented two environmental paradigms with differing realism -- the standard VLN setting built on topological environments where navigation is abstracted away, and the VLN-CE setting where agents must navigate continuous 3D environments using low-level actions. Despite sharing the high-level task and even the underlying instruction-path data, performance on VLN-CE lags behind VLN significantly. In this work, we explore this gap by transferring an agent from the abstract environment of VLN to the continuous environment of VLN-CE. We find t…
Recognizing fine-grained categories remains a challenging task, due to the subtle distinctions among different subordinate categories, which results in the need of abundant annotated samples. To alleviate the data-hungry problem, we consider the problem of learning novel categories from web data with the support of a clean set of base categories, which is referred to as weak-shot learning. In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories. Specifically, we firstly train a similarity net on clean data, and then…
Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias. Fine-tuning deep models in a new domain can require a significant amount of labeled data, which for many applications is simply not available. We propose a new CNN architecture to exploit unlabeled and sparsely labeled target domain data. Our approach simultaneously optimizes for domain invariance to facilitate domain transfer and uses a soft label distribution matching loss to transfer information between tasks. Our proposed adaptation method offers empi…
Digital Surgery（数字外科公司）；Kasetsart University（农业大学）
Surgical simulation is an increasingly important element of surgical education. Using simulation can be a means to address some of the significant challenges in developing surgical skills with limited time and resources. The photo-realistic fidelity of simulations is a key feature that can improve the experience and transfer ratio of trainees. In this paper, we demonstrate how we can enhance the visual fidelity of existing surgical simulation by performing style transfer of multi-class labels from real surgical video onto synthetic content. We demonstrate our approach on simulations of catarac…
LG AI Research（LG人工智能研究院）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources. In this paper, we propose a method (BeamCLIP) that can effectively transfer the representations of a large pre-trained multimodal model (CLIP-ViT) into a small target model (e.g., ResNet-18). For unsupervised transfer, we introduce cross-modal similarity matching (CSM) that enables a student model to learn the representations of a teacher model by matching the relative similarity distribution across text prompt embe…
In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image classification tasks. Nonetheless, training CNNs from scratch for new task or simply new data turns out to be complex and time-consuming. Recently, transfer learning has emerged as an effective methodology for adapting pre-trained CNNs to new data and classes, by only retraining the last classification layer. This paper focuses on improving this process, in order…
