相关论文: Coarse-to-Fine Q-attention: Efficient Learning for…

Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant background details. To address this issue, object-centric agents…

Recent years have witnessed great progress in deep learning based object detection. However, due to the domain shift problem, applying off-the-shelf detectors to an unseen domain leads to significant performance drop. To address such an…

Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the…

This paper demonstrates a self-supervised framework for learning voxel-wise coarse-to-fine representations tailored for dense downstream tasks. Our approach stems from the observation that existing methods for hierarchical representation…

Vector Quantization (VQ) is a method for discretizing latent representations and has become a major part of the deep learning toolkit. It has been theoretically and empirically shown that discretization of representations leads to improved…

This paper introduces a novel neural network-based reinforcement learning approach for robot gaze control. Our approach enables a robot to learn and to adapt its gaze control strategy for human-robot interaction neither with the use of…

Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning…

Finite element discretizations of problems in computational physics often rely on adaptive mesh refinement (AMR) to preferentially resolve regions containing important features during simulation. However, these spatial refinement strategies…

Solving the camera-to-robot pose is a fundamental requirement for vision-based robot control, and is a process that takes considerable effort and cares to make accurate. Traditional approaches require modification of the robot via markers,…

State-of-the-art computer vision algorithms often achieve efficiency by making discrete choices about which hypotheses to explore next. This allows allocation of computational resources to promising candidates, however, such decisions are…

Visual-inertial systems rely on precise calibrations of both camera intrinsics and inter-sensor extrinsics, which typically require manually performing complex motions in front of a calibration target. In this work we present a novel…

Robot navigation with deep reinforcement learning (RL) achieves higher performance and performs well under complex environment. Meanwhile, the interpretation of the decision-making of deep RL models becomes a critical problem for more…

Safe and efficient autonomous driving maneuvers in an interactive and complex environment can be considerably challenging due to the unpredictable actions of other surrounding agents that may be cooperative or adversarial in their…

Human activity recognition (HAR) in wearable computing is typically based on direct processing of sensor data. Sensor readings are translated into representations, either derived through dedicated preprocessing, or integrated into…

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

This study highlights the potential of image-based reinforcement learning methods for addressing swarm-related tasks. In multi-agent reinforcement learning, effective policy learning depends on how agents sense, interpret, and process…

Visual localization techniques often comprise a hierarchical localization pipeline, with a visual place recognition module used as a coarse localizer to initialize a pose refinement stage. While improving the pose refinement step has been…

Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…

Despite remarkable successes, Deep Reinforcement Learning (DRL) is not robust to hyperparameterization, implementation details, or small environment changes (Henderson et al. 2017, Zhang et al. 2018). Overcoming such sensitivity is key to…

Hierarchical coarse-to-fine policy, where a coarse branch predicts a region of interest to guide a fine-grained action predictor, has demonstrated significant potential in robotic 3D manipulation tasks by especially enhancing sample…