https://github.com/airi-institute/transpath
공식 코드TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Visual Navigation is the problem of navigating an agent, e.g. a mobile robot, in an environment using camera input only. The agent is given a target image (an image it will see from the target position), and its goal is to move from its current position to the target by applying a sequence of actions, based on the camera observations only.
Source: Vision-based Navigation Using Deep Reinforcement Learning
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers
VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation
Aerial View Localization with Reinforcement Learning: Towards Emulating Search-and-Rescue
A Survey on Mathematical Reasoning and Optimization with Large Language Models
RobustNav: Towards Benchmarking Robustness in Embodied Navigation
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
Optimistic variants of single-objective bilevel optimization for evolutionary algorithms
Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives
The Regretful Navigation Agent for Vision-and-Language Navigation
Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
Online Self-Supervised Thermal Water Segmentation for Aerial Vehicles
Learning from Unlabeled 3D Environments for Vision-and-Language Navigation
Combining Monte Carlo Tree Search and Heuristic Search for Weighted Vertex Coloring
A Training Data Recipe to Accelerate A* Search with Language Models
A Novel Point-based Algorithm for Multi-agent Control Using the Common Information Approach
SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices
Scaling and Benchmarking Self-Supervised Visual Representation Learning
VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement
SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning
SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.