Cover Image

Using large language models for embodied planning introduces systematic safety risks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Tao, Qu, Kaixian, Li, Zhibin, Wu, Jiajun, Hutter, Marco, Li, Manling, Shi, Fan
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Models
by: Zhang, Mike, et al.
Published: (2024)

IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation
by: Qu, Kaixian, et al.
Published: (2024)

Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search
by: Lee, Dongryung, et al.
Published: (2025)

A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World
by: Qu, Kaixian, et al.
Published: (2025)

Foundation models on the bridge: Semantic hazard detection and safety maneuvers for maritime autonomy with vision-language models
by: Christensen, Kim Alexander, et al.
Published: (2025)

ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning
by: Mower, Christopher E., et al.
Published: (2024)

RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
by: Wu, Kun, et al.
Published: (2024)

Trajectory Conditioned Cross-embodiment Skill Transfer
by: Tang, YuHang, et al.
Published: (2025)

Learning Adaptive Hydrodynamic Models Using Neural ODEs in Complex Conditions
by: Wang, Cong, et al.
Published: (2024)

Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
by: Li, Chenhao, et al.
Published: (2025)

Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
by: Li, Chenhao, et al.
Published: (2025)

Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion
by: Sabatini, Gianluca, et al.
Published: (2026)

End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection
by: Cui, Yu, et al.
Published: (2025)

Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why
by: Li, Chenhao, et al.
Published: (2025)

Guided Reinforcement Learning for Robust Multi-Contact Loco-Manipulation
by: Sleiman, Jean-Pierre, et al.
Published: (2024)

Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression
by: Acero, Fernando, et al.
Published: (2024)

Symmetry-Guided Memory Augmentation for Efficient Locomotion Learning
by: Bao, Kaixi, et al.
Published: (2025)

Planning with the Views via Scene Self-Exploration
by: Wang, Kangrui, et al.
Published: (2026)

Symmetry Considerations for Learning Task Symmetric Robot Policies
by: Mittal, Mayank, et al.
Published: (2024)

Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation
by: Mittal, Mayank, et al.
Published: (2021)

An Efficient Beam Search Algorithm for Active Perception in Mobile Robotics
by: Qu, Kaixian, et al.
Published: (2026)

Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation
by: Zhao, Zhe, et al.
Published: (2026)

Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
by: Hong, Yining, et al.
Published: (2026)

Efficient Learning-Based Control of a Legged Robot in Lunar Gravity
by: Arm, Philip, et al.
Published: (2025)

Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Leg
by: Arm, Philip, et al.
Published: (2024)

Learning to Open and Traverse Doors with a Legged Manipulator
by: Zhang, Mike, et al.
Published: (2024)

GenRL: Multimodal-foundation world models for generalization in embodied agents
by: Mazzaglia, Pietro, et al.
Published: (2024)

RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks
by: Chen, Yaran, et al.
Published: (2023)

DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies
by: Fan, Xianzhe, et al.
Published: (2026)

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
by: Hong, Yining, et al.
Published: (2026)

IMPASTO: Integrating Model-Based Planning with Learned Dynamics Models for Robotic Oil Painting Reproduction
by: Wang, Yingke, et al.
Published: (2026)

Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning
by: Lee, Joonho, et al.
Published: (2019)

IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
by: Liu, Yunong, et al.
Published: (2024)

System 0/1/2/3: Quad-process theory for multi-timescale embodied collective cognitive systems
by: Taniguchi, Tadahiro, et al.
Published: (2025)

D-RMGPT: Robot-assisted collaborative tasks driven by large multimodal models
by: Forlini, M., et al.
Published: (2024)

Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving
by: Lin, Haohong, et al.
Published: (2025)

Learning Planning Abstractions from Language
by: Liu, Weiyu, et al.
Published: (2024)

BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVs
by: Guo, Mingning, et al.
Published: (2025)

PIP-LLM: Integrating PDDL-Integer Programming with LLMs for Coordinating Multi-Robot Teams Using Natural Language
by: Shi, Guangyao, et al.
Published: (2025)

Value-guided action planning with JEPA world models
by: Destrade, Matthieu, et al.
Published: (2025)