Related papers: Efficient Training of Generalizable Visuomotor Pol…
Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act in varied real-world environments. However, they still fall…
Learning a policy with great generalization to unseen environments remains challenging but critical in visual reinforcement learning. Despite the success of augmentation combination in the supervised learning generalization, naively…
Automated data augmentation has shown superior performance in image recognition. Existing works search for dataset-level augmentation policies without considering individual sample variations, which are likely to be sub-optimal. On the…
Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years. However, teaching UAVs to fly in challenging environments remains an unsolved problem, mainly due to the lack of…
We tackle the problem of learning robotic sensorimotor control policies that can generalize to visually diverse and unseen environments. Achieving broad generalization typically requires large datasets, which are difficult to obtain for…
Recently, Multimodal Large Language Models (MLLMs) have sparked great research interests owing to their exceptional content-reasoning and instruction-following capabilities. To effectively instruct an MLLM, in addition to conventional…
Continual learning (CL) remains a significant challenge for deep neural networks, as it is prone to forgetting previously acquired knowledge. Several approaches have been proposed in the literature, such as experience rehearsal,…
Data augmentation is a key element for training accurate models by reducing overfitting and improving generalization. For image classification, the most popular data augmentation techniques range from simple photometric and geometrical…
The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments. Increasing the generalization capacity of the RL systems can…
Reasoning from diverse observations is a fundamental capability for generalist robot policies to operate in a wide range of environments. Despite recent advancements, many large-scale robotic policies still remain sensitive to key sources…
Visual Reinforcement Learning (RL) agents trained on limited views face significant challenges in generalizing their learned abilities to unseen views. This inherent difficulty is known as the problem of $\textit{view generalization}$. In…
Behavior cloning has shown promise for robot manipulation, but real-world demonstrations are costly to acquire at scale. While simulated data offers a scalable alternative, particularly with advances in automated demonstration generation,…
Training vision-based manipulation policies that are robust across diverse visual environments remains an important and unresolved challenge in robot learning. Current approaches often sidestep the problem by relying on invariant…
The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data…
Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an…
Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is…
Prevailing 2D-centric visuomotor policies exhibit a pronounced deficiency in novel view generalization, as their reliance on static observations hinders consistent action mapping across unseen views. In response, we introduce GenSplat, a…
Q-learning algorithms are appealing for real-world applications due to their data-efficiency, but they are very prone to overfitting and training instabilities when trained from visual observations. Prior work, namely SVEA, finds that…
Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments. To improve their generalizability, data augmentation approaches (e.g. cutout…
We study the problem of learning a generalizable action policy for an intelligent agent to actively approach an object of interest in an indoor environment solely from its visual inputs. While scene-driven or recognition-driven visual…