Papers with Code 아카이브
Robot Task Planning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 6
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zyjiao4728/POG-Demo
공식 코드https://github.com/Cassie-Lim/saycan
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
https://github.com/EmaroLab/industrialRobot_task_planning
https://github.com/MIT-SPARK/Kimera-VIO-Evaluation
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans
https://github.com/MindCode-4/code-12/tree/main/isr
ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning
https://github.com/RylanSchaeffer/prismatic-vlms
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models
https://github.com/ToniRV/Kimera-VIO-Evaluation
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans
https://github.com/ais-bonn/nimbro_api
A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service Robotics
https://github.com/bravegroup/sheetcopilot
SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models
https://github.com/clementromac/lamorel
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
https://github.com/craftjarvis/rat
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
https://github.com/davidpaulius/foon_api
Task Planning with a Weighted Functional Object-Oriented Network
https://github.com/flowersteam/lamorel
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
https://github.com/microsoft/recai
Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
https://github.com/princeton-nlp/swe-agent
NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
https://github.com/pwc-1/Paper-5/tree/main/mpt
MPTP: Motion-Planning-aware Task Planning for Navigation in Belief Space
https://github.com/swe-agent/swe-agent
NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
https://github.com/ubiquitouslearning/mllm
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
https://github.com/wenbowen123/BundleTrack
You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.