Previous work optimizes traditional active learning (AL) processes with incremental neural network architecture search (Active-iNAS) based on data complexity change, which improves the accuracy and learning efficiency. However, Active-iNAS trains several models and selects the model with the best generalization performance for querying the subsequent samples after each active learning cycle. The independent training processes lead to an insufferable computational budget, which is significantly inefficient and limits search flexibility and final performance. To address this issue, we propose a novel active strategy with the method called structured variational inference (SVI) or structured neural depth search (SNDS) whereby we could use the gradient descent method in neural network depth search during AL processes. At the same time, we theoretically demonstrate that the current VI-based methods based on the mean-field assumption could lead to poor performance. We apply our strategy using three querying techniques and three datasets and show that our strategy outperforms current methods.
Ground-air negotiation via speech communication is a vital prerequisite for ensuring safety and efficiency in air traffic control (ATC) operations. However, with the increase in traffic flow, incorrect instructions caused by human factors bring a great threat to ATC safety. Existing flight trajectory prediction (FTP) approaches primarily rely on the flight status of historical trajectory, leading to significant delays in the prediction of real-time maneuvering instruction, which is not conducive to conflict detection. A major reason is that spoken instructions and flight trajectories are presented in different modalities in the current air traffic control (ATC) system, bringing great challenges to considering the maneuvering instruction in the FTP tasks. In this paper, a spoken instruction-aware FTP framework, called SIA-FTP, is innovatively proposed to support high-maneuvering FTP tasks by incorporating instant spoken instruction. To address the modality gap and minimize the data requirements, a 3-stage learning paradigm is proposed to implement the SIA-FTP framework in a progressive manner, including trajectory-based FTP pretraining, intent-oriented instruction embedding learning, and multi-modal finetuning. Specifically, the FTP model and the instruction embedding with maneuvering semantics are pre-trained using volumes of well-resourced trajectory and text data in the 1st and 2nd stages. In succession, a multi-modal fusion strategy is proposed to incorporate the pre-trained instruction embedding into the FTP model and integrate the two pre-trained networks into a joint model. Finally, the joint model is finetuned using the limited trajectory-instruction data to enhance the FTP performance within maneuvering instruction scenarios. The experimental results demonstrated that the proposed framework presents an impressive performance improvement in high-maneuvering scenarios.
Flight Trajectory Prediction (FTP) is an essential task in Air Traffic Control (ATC), which can assist air traffic controllers to manage airspace more safely and efficiently. Existing approaches generally perform multi-horizon FTP tasks in an autoregressive manner, which is prone to suffer from error accumulation and low-efficiency problems. In this paper, a novel framework, called FlightBERT++, is proposed to i) forecast multi-horizon flight trajectories directly in a non-autoregressive way, and ii) improved the limitation of the binary encoding (BE) representation in the FlightBERT framework. Specifically, the proposed framework is implemented by a generalized Encoder-Decoder architecture, in which the encoder learns the temporal-spatial patterns from historical observations and the decoder predicts the flight status for the future time steps. Compared to conventional architecture, an extra horizon-aware contexts generator (HACG) is dedicatedly designed to consider the prior horizon information that enables us to perform multi-horizon non-autoregressive prediction. Additionally, a differential prediction strategy is designed by well considering both the stationarity of the differential sequence and the high-bits errors of the BE representation. Moreover, the Bit-wise Weighted Binary Cross Entropy loss function is proposed to optimize the proposed framework that can further constrain the high-bits errors of the predictions. Finally, the proposed framework is validated on a real-world flight trajectory dataset. The experimental results show that the proposed framework outperformed the competitive baselines.
Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, \emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories; 2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories.
Accurate estimation of the relative pose between an object and a robot hand is critical for many manipulation tasks. However, most of the existing object-in-hand pose datasets use two-finger grippers and also assume that the object remains fixed in the hand without any relative movements, which is not representative of real-world scenarios. To address this issue, a 6D object-in-hand pose dataset is proposed using a teleoperation method with an anthropomorphic Shadow Dexterous hand. Our dataset comprises RGB-D images, proprioception and tactile data, covering diverse grasping poses, finger contact states, and object occlusions. To overcome the significant hand occlusion and limited tactile sensor contact in real-world scenarios, we propose PoseFusion, a hybrid multi-modal fusion approach that integrates the information from visual and tactile perception channels. PoseFusion generates three candidate object poses from three estimators (tactile only, visual only, and visuo-tactile fusion), which are then filtered by a SelectLSTM network to select the optimal pose, avoiding inferior fusion poses resulting from modality collapse. Extensive experiments demonstrate the robustness and advantages of our framework. All data and codes are available on the project website: https://elevenjiang1.github.io/ObjectInHand-Dataset/
Grasping an object when it is in an ungraspable pose is a challenging task, such as books or other large flat objects placed horizontally on a table. Inspired by human manipulation, we address this problem by pushing the object to the edge of the table and then grasping it from the hanging part. In this paper, we develop a model-free Deep Reinforcement Learning framework to synergize pushing and grasping actions. We first pre-train a Variational Autoencoder to extract high-dimensional features of input scenario images. One Proximal Policy Optimization algorithm with the common reward and sharing layers of Actor-Critic is employed to learn both pushing and grasping actions with high data efficiency. Experiments show that our one network policy can converge 2.5 times faster than the policy using two parallel networks. Moreover, the experiments on unseen objects show that our policy can generalize to the challenging case of objects with curved surfaces and off-center irregularly shaped objects. Lastly, our policy can be transferred to a real robot without fine-tuning by using CycleGAN for domain adaption and outperforms the push-to-wall baseline.
Precise robotic grasping of several novel objects is a huge challenge in manufacturing, automation, and logistics. Most of the current methods for model-free grasping are disadvantaged by the sparse data in grasping datasets and by errors in sensor data and contact models. This study combines data generation and sim-to-real transfer learning in a grasping framework that reduces the sim-to-real gap and enables precise and reliable model-free grasping. A large-scale robotic grasping dataset with dense grasp labels is generated using domain randomization methods and a novel data augmentation method for deep learning-based robotic grasping to solve data sparse problem. We present an end-to-end robotic grasping network with a grasp optimizer. The grasp policies are trained with sim-to-real transfer learning. The presented results suggest that our grasping framework reduces the uncertainties in grasping datasets, sensor data, and contact models. In physical robotic experiments, our grasping framework grasped single known objects and novel complex-shaped household objects with a success rate of 90.91%. In a complex scenario with multi-objects robotic grasping, the success rate was 85.71%. The proposed grasping framework outperformed two state-of-the-art methods in both known and unknown object robotic grasping.
Accurate acne detection plays a crucial role in acquiring precise diagnosis and conducting proper therapy. However, the ambiguous boundaries and arbitrary dimensions of acne lesions severely limit the performance of existing methods. In this paper, we address these challenges via a novel Decoupled Sequential Detection Head (DSDH), which can be easily adopted by mainstream two-stage detectors. DSDH brings two simple but effective improvements to acne detection. Firstly, the offset and scaling tasks are explicitly introduced, and their incompatibility is settled by our task-decouple mechanism, which improves the capability of predicting the location and size of acne lesions. Second, we propose the task-sequence mechanism, and execute offset and scaling sequentially to gain a more comprehensive insight into the dimensions of acne lesions. In addition, we build a high-quality acne detection dataset named ACNE-DET to verify the effectiveness of DSDH. Experiments on ACNE-DET and the public benchmark ACNE04 show that our method outperforms the state-of-the-art methods by significant margins. Our code and dataset are publicly available at (temporarily anonymous).
Approximately 1.2% of the world's population has impaired voice production. As a result, automatic dysphonic voice detection has attracted considerable academic and clinical interest. However, existing methods for automated voice assessment often fail to generalize outside the training conditions or to other related applications. In this paper, we propose a deep learning framework for generating acoustic feature embeddings sensitive to vocal quality and robust across different corpora. A contrastive loss is combined with a classification loss to train our deep learning model jointly. Data warping methods are used on input voice samples to improve the robustness of our method. Empirical results demonstrate that our method not only achieves high in-corpus and cross-corpus classification accuracy but also generates good embeddings sensitive to voice quality and robust across different corpora. We also compare our results against three baseline methods on clean and three variations of deteriorated in-corpus and cross-corpus datasets and demonstrate that the proposed model consistently outperforms the baseline methods.
Currently, task-oriented grasp detection approaches are mostly based on pixel-level affordance detection and semantic segmentation. These pixel-level approaches heavily rely on the accuracy of a 2D affordance mask, and the generated grasp candidates are restricted to a small workspace. To mitigate these limitations, we first construct a novel affordance-based grasp dataset and propose a 6-DoF task-oriented grasp detection framework, which takes the observed object point cloud as input and predicts diverse 6-DoF grasp poses for different tasks. Specifically, our implicit estimation network and visual affordance network in this framework could directly predict coarse grasp candidates, and corresponding 3D affordance heatmap for each potential task, respectively. Furthermore, the grasping scores from coarse grasps are combined with heatmap values to generate more accurate and finer candidates. Our proposed framework shows significant improvements compared to baselines for existing and novel objects on our simulation dataset. Although our framework is trained based on the simulated objects and environment, the final generated grasp candidates can be accurately and stably executed in real robot experiments when the object is randomly placed on a support surface.