paper-with-me

Papers

Human-Centered Planning

2023-11-08 · Yuliang Li, Nitin Kamra, Ruta Desai, Alon Halevy

LLMs have recently made impressive inroads on tasks whose output is structured, such as coding, robotic planning and querying databases. The vision of creating AI-powered personal assistants also involves creating structured outputs, such as a plan for one's day, or for an overseas trip. Here, since the plan is executed by a human, the output doesn't have to satisfy strict syntactic constraints. A useful assistant should also be able to incorporate vague constraints specified by the user in natural language. This makes LLMs an attractive option for planning. We consider the problem of planning one's day. We develop an LLM-based planner (LLMPlan) extended with the ability to self-reflect on its output and a symbolic planner (SymPlan) with the ability to translate text constraints into a symbolic representation. Despite no formal specification of constraints, we find that LLMPlan performs explicit constraint satisfaction akin to the traditional symbolic planners on average (2% performance difference), while retaining the reasoning of implicit requirements. Consequently, LLM-based planners outperform their symbolic counterparts in user satisfaction (70.5% vs. 40.4%) during interactive evaluation with 40 users.

📄 PDF Abstract BibTeX arXiv:2311.04403

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots

2026-03-10 · Boxun Hu, Chang Chang, Jiawei Ge, Man Namgung 외 arxiv

We naturally step sideways or lean to see around the obstacle when our view is blocked, and recover a more informative observation. Enabling robots to make the same kind of viewpoint choice is critical for human-centered…

Motion Planning

SMASH: a Semantic-enabled Multi-agent Approach for Self-adaptation of Human-centered IoT

2021-05-31 · Hamed Rahimi, Iago Felipe Trentin, Fano Ramparany, Olivier Boissier

Nowadays, IoT devices have an enlarging scope of activities spanning from sensing, computing to acting and even more, learning, reasoning and planning. As the number of IoT applications increases, these objects are becom…

Multi-agent Integration

A Human-Centered Data-Driven Planner-Actor-Critic Architecture via Logic Programming

2019-09-18 · Daoming Lyu, Fangkai Yang, Bo Liu, Steven Gustafson

Recent successes of Reinforcement Learning (RL) allow an agent to learn policies that surpass human experts but suffers from being time-hungry and data-hungry. By contrast, human learning is significantly faster because …

General KnowledgeReinforcement LearningReinforcement Learning (RL)

Towards Human-centered Proactive Conversational Agents

2024-04-19 · Yang Deng, Lizi Liao, Zhonghua Zheng, Grace Hui Yang 외

Recent research on proactive conversational agents (PCAs) mainly focuses on improving the system's capabilities in anticipating and planning action sequences to accomplish tasks and achieve goals before users articulate …

Information RetrievalRetrieval

Towards Probabilistic Planning of Explanations for Robot Navigation

2024-10-26 · Amar Halilovic, Senka Krivic

In robotics, ensuring that autonomous systems are comprehensible and accountable to users is essential for effective human-robot interaction. This paper introduces a novel approach that integrates user-centered design pr…

Robot Navigation