相关论文: Multitask Learning for Multiple Recognition Tasks:…

Jointly learning multiple tasks with a unified model can improve accuracy and data efficiency, but it faces the challenge of task interference, where optimizing one task objective may inadvertently compromise the performance of another. A…

Multi-robot control in cluttered environments is a challenging problem that involves complex physical constraints, including robot-robot collisions, robot-obstacle collisions, and unreachable motions. Successful planning in such settings…

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a…

This paper presents a novel multitask multiple kernel learning framework that efficiently learns the kernel weights leveraging the relationship across multiple tasks. The idea is to automatically infer this task relationship in the…

Recognizing driving behaviors is important for downstream tasks such as reasoning, planning, and navigation. Existing video recognition approaches work well for common behaviors (e.g. "drive straight", "brake", "turn left/right"). However,…

Recent progress in legged locomotion has allowed highly dynamic and parkour-like behaviors for robots, similar to their biological counterparts. Yet, these methods mostly rely on egocentric (first-person) perception, limiting their…

Lower limbs exoskeletons provide assistance during standing, squatting, and walking. Gait dynamics, in particular, implies a change in the configuration of the device in terms of contact points, actuation, and system dynamics in general. In…

Multiple mobile robots play a significant role in various spatially distributed tasks.In unfamiliar and non-repetitive scenarios, reconstructing the global map is time-inefficient and sometimes unrealistic. Hence, research has focused on…

Representation learning based on multi-task pretraining has become a powerful approach in many domains. In particular, task-aware representation learning aims to learn an optimal representation for a specific target task by sampling data…

A long-standing question in robot hand design is how accurate tactile sensing must be. This paper uses simulated tactile signals and the reinforcement learning (RL) framework to study the sensing needs in grasping systems. Our first…

Multitask learning is widely used in practice to train a low-resource target task by augmenting it with multiple related source tasks. Yet, naively combining all the source tasks with a target task does not always improve the prediction…

Underwater acoustic target recognition has emerged as a prominent research area within the field of underwater acoustics. However, the current availability of authentic underwater acoustic signal recordings remains limited, which hinders…

Task Parametrized Gaussian Mixture Models (TP-GMM) are a sample-efficient method for learning object-centric robot manipulation tasks. However, there are several open challenges to applying TP-GMMs in the wild. In this work, we tackle three…

Multi-robot systems such as swarms of aerial robots are naturally suited to offer additional flexibility, resilience, and robustness in several tasks compared to a single robot by enabling cooperation among the agents. To enhance the…

Task-aware robotic grasping is a challenging problem that requires the integration of semantic understanding and geometric reasoning. This paper proposes a novel framework that leverages Large Language Models (LLMs) and Quality Diversity…

Recent advances in robot learning have enabled robots to become increasingly better at mastering a predefined set of tasks. On the other hand, as humans, we have the ability to learn a growing set of tasks over our lifetime. Continual robot…

Representation multi-task learning (MTL) has achieved tremendous success in practice. However, the theoretical understanding of these methods is still lacking. Most existing theoretical works focus on cases where all tasks share the same…

The trace norm is widely used in multi-task learning as it can discover low-rank structures among tasks in terms of model parameters. Nowadays, with the emerging of big datasets and the popularity of deep learning techniques, tensor trace…

In this study, we introduce an innovative EEG signal reconstruction sub-module designed to enhance the performance of deep learning models on EEG eye-tracking tasks. This sub-module can integrate with all Encoder-Classifier-based deep…

Multitask learning is a widely recognized technique in the field of computer vision and deep learning domain. However, it is still a research question in remote sensing, particularly for hyperspectral imaging. Moreover, most of the research…