Shared Multi-Task Imitation Learning for Indoor Self-Navigation
Deep imitation learning enables robots to learn from expert demonstrations to perform tasks such as lane following or obstacle avoidance. However, in the traditional imitation learning framework, one model only learns one task, and thus it lacks of the capability to support a robot to perform various different navigation tasks with one model in indoor environments. This paper proposes a new framework, Shared Multi-headed Imitation Learning(SMIL), that allows a robot to perform multiple tasks with one model without switching among different models. We model each task as a sub-policy and design a multi-headed policy to learn the shared information among related tasks by summing up activations from all sub-policies. Compared to single or non-shared multi-headed policies, this framework is able to leverage correlated information among tasks to increase performance.We have implemented this framework using a robot based on NVIDIA TX2 and performed extensive experiments in indoor environments with different baseline solutions. The results demonstrate that SMIL has doubled the performance over nonshared multi-headed policy.
Code (0)
등록된 구현이 없습니다.
Tasks
Imitation LearningSimilar Papers 제목 키워드 기반
Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Critic Controller
This paper presents a cooperative indoor UAV guidance framework that combines a shared voxel-map world model with a multi-agent Soft Actor-Critic (MASAC) controller. Multiple drones fuse 360 LiDAR observations into a com…
Continuous ControlExploiting Multiple Priors for Neural 3D Indoor Reconstruction
Neural implicit modeling permits to achieve impressive 3D reconstruction results on small objects, while it exhibits significant limitations in large indoor scenes. In this work, we propose a novel neural implicit modeli…
3D ReconstructionIndoor 3D Video Monitoring Using Multiple Kinect Depth-Cameras
This article describes the design and development of a system for remote indoor 3D monitoring using an undetermined number of Microsoft(R) Kinect sensors. In the proposed client-server system, the Kinect cameras can be c…
DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation
Indoor semantic segmentation is fundamental to computer vision and robotics, supporting applications such as autonomous navigation, augmented reality, and smart environments. Although RGB-D fusion leverages complementary…
Semantic SegmentationScene SegmentationOFVL-MS: Once for Visual Localization across Multiple Indoor Scenes
In this work, we seek to predict camera poses across scenes with a multi-task learning manner, where we view the localization of each scene as a new task. We propose OFVL-MS, a unified framework that dispenses with the t…
Multi-Task LearningVisual Localization