Multiple robot systems are favored for object manipulation and transportation, especially for large objects. However, in more complex manipulation such as flipping, these systems encounter a new challenge, configuration disconnectivity of manipulators. Grasping objects by manipulators will impose closed-chain constraints on the system, which in turn limits the feasible motions of manipulators and further compromises the configuration connectivity. Multiple mobile manipulator systems show much more flexibility in object manipulation with the mobility of the mobile platform and have the potential to address the above problem. In this paper, a novel planning framework is proposed for complex flipping manipulation by incorporating platform motions and regrasping. Firstly, two types of trajectories, mobile manipulator planning and regrasping planning, are classified and can be assigned different priorities for different tasks. Secondly, corresponding planning methods are designed for each type of trajectory. Specifically, in mobile manipulator planning, the configuration of the platform is determined through optimization to ensure connectivity when the manipulator approaches configuration boundaries. In regrasping planning, closed-chain constraints are temporarily disregarded and the manipulation capabilities are prioritized to facilitate subsequent planning. Finally, the structure of the overall planning framework is provided. Experimental results demonstrate that the proposed planner efficiently plans the motions of the system to accomplish flipping manipulation. Additionally, a comprehensive experiment emphasizes the significance of our planner in extending the capabilities of multiple mobile manipulator systems in complex tasks.
Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and zero-shot capabilities. To enhance the performance of pre-trained models for downstream tasks, fine-tuning the model on downstream data is frequently necessary. However, fine-tuning the pre-trained model leads to a decrease in its generalizability in the presence of distribution shift, while the limited number of samples in few-shot learning makes the model highly susceptible to overfitting. Consequently, existing methods for fine-tuning few-shot learning primarily focus on fine-tuning the model's classification head or introducing additional structure. In this paper, we introduce a fine-tuning approach termed Feature Discrimination Alignment (FD-Align). Our method aims to bolster the model's generalizability by preserving the consistency of spurious features across the fine-tuning process. Extensive experimental results validate the efficacy of our approach for both ID and OOD tasks. Once fine-tuned, the model can seamlessly integrate with existing methods, leading to performance improvements. Our code can be found in https://github.com/skingorz/FD-Align.
Topological maps are favorable for their small storage compared to geometric map. However, they are limited in relocalization and path planning capabilities. To solve this problem, a feature-based hierarchical topological map (FHT-Map) is proposed along with a real-time map construction algorithm for robot exploration. Specifically, the FHT-Map utilizes both RGB cameras and LiDAR information and consists of two types of nodes: main node and support node. Main nodes will store visual information compressed by convolutional neural network and local laser scan data to enhance subsequent relocalization capability. Support nodes retain a minimal amount of data to ensure storage efficiency while facilitating path planning. After map construction with robot exploration, the FHT-Map can be used by other robots for relocalization and path planning. Experiments are conducted in Gazebo simulator, and the results demonstrate that the proposed FHT-Map can effectively improve relocalization and path planning capability compared with other topological maps. Moreover, experiments on hierarchical architecture are implemented to show the necessity of two types of nodes.
This paper describes the NPU-MSXF system for the IWSLT 2023 speech-to-speech translation (S2ST) task which aims to translate from English speech of multi-source to Chinese speech. The system is built in a cascaded manner consisting of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS). We make tremendous efforts to handle the challenging multi-source input. Specifically, to improve the robustness to multi-source speech input, we adopt various data augmentation strategies and a ROVER-based score fusion on multiple ASR model outputs. To better handle the noisy ASR transcripts, we introduce a three-stage fine-tuning strategy to improve translation accuracy. Finally, we build a TTS model with high naturalness and sound quality, which leverages a two-stage framework, using network bottleneck features as a robust intermediate representation for speaker timbre and linguistic content disentanglement. Based on the two-stage framework, pre-trained speaker embedding is leveraged as a condition to transfer the speaker timbre in the source English speech to the translated Chinese speech. Experimental results show that our system has high translation accuracy, speech naturalness, sound quality, and speaker similarity. Moreover, it shows good robustness to multi-source data.
Direct speech-to-speech translation (S2ST) has gradually become popular as it has many advantages compared with cascade S2ST. However, current research mainly focuses on the accuracy of semantic translation and ignores the speech style transfer from a source language to a target language. The lack of high-fidelity expressive parallel data makes such style transfer challenging, especially in more practical zero-shot scenarios. To solve this problem, we first build a parallel corpus using a multi-lingual multi-speaker text-to-speech synthesis (TTS) system and then propose the StyleS2ST model with cross-lingual speech style transfer ability based on a style adaptor on a direct S2ST system framework. Enabling continuous style space modeling of an acoustic model through parallel corpus training and non-parallel TTS data augmentation, StyleS2ST captures cross-lingual acoustic feature mapping from the source to the target language. Experiments show that StyleS2ST achieves good style similarity and naturalness in both in-set and out-of-set zero-shot scenarios.
Due to the scarcity of available data, deep learning does not perform well on few-shot learning tasks. However, human can quickly learn the feature of a new category from very few samples. Nevertheless, previous work has rarely considered how to mimic human cognitive behavior and apply it to few-shot learning. This paper introduces Gestalt psychology to few-shot learning and proposes Gestalt-Guided Image Understanding, a plug-and-play method called GGIU. Referring to the principle of totality and the law of closure in Gestalt psychology, we design Totality-Guided Image Understanding and Closure-Guided Image Understanding to extract image features. After that, a feature estimation module is used to estimate the accurate features of images. Extensive experiments demonstrate that our method can improve the performance of existing models effectively and flexibly without retraining or fine-tuning. Our code is released on https://github.com/skingorz/GGIU.
Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a challenging cross-modal retrieval task. In prior arts, the retrieval is conducted by sorting the distance between the query sketch and each image in the gallery. However, the domain gap and the zero-shot setting make neural networks hard to generalize. This paper tackles the challenges from a new perspective: utilizing gallery image features. We propose a Cluster-then-Retrieve (ClusterRetri) method that performs clustering on the gallery images and uses the cluster centroids as proxies for retrieval. Furthermore, a distribution alignment loss is proposed to align the image and sketch features with a common Gaussian distribution, reducing the domain gap. Despite its simplicity, our proposed method outperforms the state-of-the-art methods by a large margin on popular datasets, e.g., up to 31% and 39% relative improvement of mAP@all on the Sketchy and TU-Berlin datasets.
This paper aims to synthesize target speaker's speech with desired speaking style and emotion by transferring the style and emotion from reference speech recorded by other speakers. Specifically, we address this challenging problem with a two-stage framework composed of a text-to-style-and-emotion (Text2SE) module and a style-and-emotion-to-wave (SE2Wave) module, bridging by neural bottleneck (BN) features. To further solve the multi-factor (speaker timbre, speaking style and emotion) decoupling problem, we adopt the multi-label binary vector (MBV) and mutual information (MI) minimization to respectively discretize the extracted embeddings and disentangle these highly entangled factors in both Text2SE and SE2Wave modules. Moreover, we introduce a semi-supervised training strategy to leverage data from multiple speakers, including emotion-labelled data, style-labelled data, and unlabeled data. To better transfer the fine-grained expressiveness from references to the target speaker in the non-parallel transfer, we introduce a reference-candidate pool and propose an attention based reference selection approach. Extensive experiments demonstrate the good design of our model.