相关论文: End-to-end Active Object Tracking via Reinforcemen…

This paper presents an end-to-end approach for tracking static and dynamic objects for an autonomous vehicle driving through crowded urban environments. Unlike traditional approaches to tracking, this method is learned end-to-end, and is…

Deep Reinforcement Learning has proved to be able to solve many control tasks in different fields, but the behavior of these systems is not always as expected when deployed in real-world scenarios. This is mainly due to the lack of domain…

Due to implicitly introduced periodic shifting of limited searching area, visual object tracking using correlation filters often has to confront undesired boundary effect. As boundary effect severely degrade the quality of object model, it…

Efficient and accurate object detection is an important topic in the development of computer vision systems. With the advent of deep learning techniques, the accuracy of object detection has increased significantly. The project aims to…

The increasing need for automated visual monitoring and control for applications such as smart camera surveillance, traffic monitoring, and intelligent environments, necessitates the improvement of methods for visual active monitoring.…

The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames. Standard motion estimators used in tracking, e.g., Long Short Term Memory (LSTM), only deal with single…

Learning whole-body control for locomotion and arm motions in a single policy has challenges, as the two tasks have conflicting goals. For instance, efficient locomotion typically favors a horizontal base orientation, while end-effector…

In this paper we propose a novel approach to tracking by detection that can exploit both cameras as well as LIDAR data to produce very accurate 3D trajectories. Towards this goal, we formulate the problem as a linear program that can be…

Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2)…

Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with…

The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to…

Visual active tracking is a growing research topic in robotics due to its key role in applications such as human assistance, disaster recovery, and surveillance. In contrast to passive tracking, active tracking approaches combine vision and…

This paper proposes an end-to-end deep reinforcement learning approach for mobile robot navigation with dynamic obstacles avoidance. Using experience collected in a simulation environment, a convolutional neural network (CNN) is trained to…

Achieving robust vision-based humanoid locomotion remains challenging due to two fundamental issues: the sim-to-real gap introduces significant perception noise that degrades performance on fine-grained tasks, and training a unified policy…

Manipulation of deformable objects is a challenging task for a robot. It will be problematic to use a single sensory input to track the behaviour of such objects: vision can be subjected to occlusions, whereas tactile inputs cannot capture…

Visual object tracking task is constantly gaining importance in several fields of application as traffic monitoring, robotics, and surveillance, to name a few. Dealing with changes in the appearance of the tracked object is paramount to…

Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic…

A model used for velocity control during car following was proposed based on deep reinforcement learning (RL). To fulfil the multi-objectives of car following, a reward function reflecting driving safety, efficiency, and comfort was…

Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…

Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…