Recognizing and grasping novel-category objects remains a crucial yet challenging problem in real-world robotic applications. Despite its significance, limited research has been conducted in this specific domain. To address this, we seamlessly propose a novel framework that integrates open-vocabulary learning into the domain of robotic grasping, empowering robots with the capability to adeptly handle novel objects. Our contributions are threefold. Firstly, we present a large-scale benchmark dataset specifically tailored for evaluating the performance of open-vocabulary grasping tasks. Secondly, we propose a unified visual-linguistic framework that serves as a guide for robots in successfully grasping both base and novel objects. Thirdly, we introduce two alignment modules designed to enhance visual-linguistic perception in the robotic grasping process. Extensive experiments validate the efficacy and utility of our approach. Notably, our framework achieves an average accuracy of 71.2\% and 64.4\% on base and novel categories in our new dataset, respectively.

The expanding research on manifold-based self-supervised learning (SSL) builds on the manifold hypothesis, which suggests that the inherent complexity of high-dimensional data can be unraveled through lower-dimensional manifold embeddings. Capitalizing on this, DeepInfomax with an unbalanced atlas (DIM-UA) has emerged as a powerful tool and yielded impressive results for state representations in reinforcement learning. Meanwhile, Maximum Manifold Capacity Representation (MMCR) presents a new frontier for SSL by optimizing class separability via manifold compression. However, MMCR demands extensive input views, resulting in significant computational costs and protracted pre-training durations. Bridging this gap, we present an innovative integration of MMCR into existing SSL methods, incorporating a discerning regularization strategy that enhances the lower bound of mutual information. We also propose a novel state representation learning method extending DIM-UA, embedding a nuclear norm loss to enforce manifold consistency robustly. On experimentation with the Atari Annotated RAM Interface, our method improves DIM-UA significantly with the same number of target encoding dimensions. The mean F1 score averaged over categories is 78% compared to 75% of DIM-UA. There are also compelling gains when implementing SimCLR and Barlow Twins. This supports our SSL innovation as a paradigm shift, enabling more nuanced high-dimensional data representations.

This research reports VascularPilot3D, the first 3D fully autonomous endovascular robot navigation system. As an exploration toward autonomous guidewire navigation, VascularPilot3D is developed as a complete navigation system based on intra-operative imaging systems (fluoroscopic X-ray in this study) and typical endovascular robots. VascularPilot3D adopts previously researched fast 3D-2D vessel registration algorithms and guidewire segmentation methods as its perception modules. We additionally propose three modules: a topology-constrained 2D-3D instrument end-point lifting method, a tree-based fast path planning algorithm, and a prior-free endovascular navigation strategy. VascularPilot3D is compatible with most mainstream endovascular robots. Ex-vivo experiments validate that VascularPilot3D achieves 100% success rate among 25 trials. It reduces the human surgeon's overall control loops by 18.38%. VascularPilot3D is promising for general clinical autonomous endovascular navigations.

Vision Transformers implement multi-head self-attention (MSA) via stacking multiple attention blocks. The query, key, and value are often intertwined and generated within those blocks via a single, shared linear transformation. This paper explores the concept of disentangling the key from the query and value, and adopting a manifold representation for the key. Our experiments reveal that decoupling and endowing the key with a manifold structure can enhance the model performance. Specifically, ViT-B exhibits a 0.87% increase in top-1 accuracy, while Swin-T sees a boost of 0.52% in top-1 accuracy on the ImageNet-1K dataset, with eight charts in the manifold key. Our approach also yields positive results in object detection and instance segmentation tasks on the COCO dataset. Through detailed ablation studies, we establish that these performance gains are not merely due to the simplicity of adding more parameters and computations. Future research may investigate strategies for cutting the budget of such representations and aim for further performance improvements based on our findings.

Transformers are neural network models that utilize multiple layers of self-attention heads and have exhibited enormous potential in natural language processing tasks. Meanwhile, there have been efforts to adapt transformers to visual tasks of machine learning, including Vision Transformers and Swin Transformers. Although some researchers use Vision Transformers for reinforcement learning tasks, their experiments remain at a small scale due to the high computational cost. Experiments conducted at a large scale, on the other hand, have to rely on techniques to cut the costs of Vision Transformers, which also yield inferior results. To address this challenge, this article presents the first online reinforcement learning scheme that is based on Swin Transformers: Swin DQN. Swin Transformers are promising as a backbone in neural networks by splitting groups of image pixels into small patches and applying local self-attention operations inside the (shifted) windows of fixed sizes. They have demonstrated state-of-the-art performances in benchmarks. In contrast to existing research, our novel approach is reducing the computational costs, as well as significantly improving the performance. We demonstrate the superior performance with experiments on 49 games in the Arcade Learning Environment. The results show that our approach, using Swin Transformers with Double DQN, achieves significantly higher maximal evaluation scores than the baseline method in 45 of all the 49 games ~92%, and higher mean evaluation scores than the baseline method in 40 of all the 49 games ~82%.

The manifold hypothesis posits that high-dimensional data often lies on a lower-dimensional manifold and that utilizing this manifold as the target space yields more efficient representations. While numerous traditional manifold-based techniques exist for dimensionality reduction, their application in self-supervised learning has witnessed slow progress. The recent MSIMCLR method combines manifold encoding with SimCLR but requires extremely low target encoding dimensions to outperform SimCLR, limiting its applicability. This paper introduces a novel learning paradigm using an unbalanced atlas (UA), capable of surpassing state-of-the-art self-supervised learning approaches. We meticulously investigated and engineered the DeepInfomax with an unbalanced atlas (DIM-UA) method by systematically adapting the Spatiotemporal DeepInfomax (ST-DIM) framework to align with our proposed UA paradigm, employing rigorous scientific methodologies throughout the process. The efficacy of DIM-UA is demonstrated through training and evaluation on the Atari Annotated RAM Interface (AtariARI) benchmark, a modified version of the Atari 2600 framework that produces annotated image samples for representation learning. The UA paradigm improves the existing algorithm significantly when the number of target encoding dimensions grows. For instance, the mean F1 score averaged over categories of DIM-UA is ~75% compared to ~70% of ST-DIM when using 16384 hidden units.

State representation learning aims to capture latent factors of an environment. Contrastive methods have performed better than generative models in previous state representation learning research. Although some researchers realize the connections between masked image modeling and contrastive representation learning, the effort is focused on using masks as an augmentation technique to represent the latent generative factors better. Partially observable environments in reinforcement learning have not yet been carefully studied using unsupervised state representation learning methods. In this article, we create an unsupervised state representation learning scheme for partially observable states. We conducted our experiment on a previous Atari 2600 framework designed to evaluate representation learning models. A contrastive method called Spatiotemporal DeepInfomax (ST-DIM) has shown state-of-the-art performance on this benchmark but remains inferior to its supervised counterpart. Our approach improves ST-DIM when the environment is not fully observable and achieves higher F1 scores and accuracy scores than the supervised learning counterpart. The mean accuracy score averaged over categories of our approach is ~66%, compared to ~38% of supervised learning. The mean F1 score is ~64% to ~33%.

We propose a novel algorithm named Expert Q-learning. Expert Q-learning was inspired by Dueling Q-learning and aimed at incorporating the ideas from semi-supervised learning into reinforcement learning through splitting Q-values into state values and action advantages. Different from Generative Adversarial Imitation Learning and Deep Q-Learning from Demonstrations, the offline expert we have used only predicts the value of a state from {-1, 0, 1}, indicating whether this is a bad, neutral or good state. An expert network was designed in addition to the Q-network, which updates each time following the regular offline minibatch update whenever the expert example buffer is not empty. The Q-network plays the role of the advantage function only during the update. Our algorithm also keeps asynchronous copies of the Q-network and expert network, predicting the target values using the same manner as of Double Q-learning. We compared on the game of Othello our algorithm with the state-of-the-art Q-learning algorithm, which was a combination of Double Q-learning and Dueling Q-learning. The results showed that Expert Q-learning was indeed useful and more resistant to the overestimation bias of Q-learning. The baseline Q-learning algorithm exhibited unstable and suboptimal behavior, especially when playing against a stochastic player, whereas Expert Q-learning demonstrated more robust performance with higher scores. Expert Q-learning without using examples has also gained better results than the baseline algorithm when trained and tested against a fixed player. On the other hand, Expert Q-learning without examples cannot win against the baseline Q-learning algorithm in direct game competitions despite the fact that it has also shown the strength of reducing the overestimation bias.

In this paper we investigate the feasibility of using synthetic data to augment face datasets. In particular, we propose a novel generative adversarial network (GAN) that can disentangle identity-related attributes from non-identity-related attributes. This is done by training an embedding network that maps discrete identity labels to an identity latent space that follows a simple prior distribution, and training a GAN conditioned on samples from that distribution. Our proposed GAN allows us to augment face datasets by generating both synthetic images of subjects in the training set and synthetic images of new subjects not in the training set. By using recent advances in GAN training, we show that the synthetic images generated by our model are photo-realistic, and that training with augmented datasets can indeed increase the accuracy of face recognition models as compared with models trained with real images alone.