Embodiment Meets Environment: Toward Context-Aware, Safe Physical Caregiving Robots

2026-06-26

AI Summary

Existing physical care robots struggle to safely and generically transfer skills across diverse environments and tasks due to their lack of explicit modeling of human–robot–environment context. This work proposes the E²-CARE framework, which uniquely treats the joint context formed by the robot embodiment and its environment as the core basis for adaptation. It explicitly represents interaction context through a unified 3D dynamic scene graph and encodes caregiving skills as online-reshapable interaction templates. By integrating runtime constraint synthesis with safety-aware control, the framework enables zero-shot cross-platform skill reuse. Extensive experiments evaluate four activities of daily living across hundreds of simulated home scenarios, and real-world multi-environment user studies with dual robotic platforms confirm the method’s consistency and effectiveness.

Abstract

Physical caregiving robots need to assist different users with different tasks in diverse environments, and they come in many embodiments. While substantial progress has been made on individual caregiving tasks, most existing systems remain tightly coupled to specific environments and robot embodiments, and often do not explicitly model or constrain interactions around people, despite humans being special agents in the environment. This motivates a focus on adapting to context that emerges from the joint interaction between the environment and the robot's embodiment. We propose $E^2$-CARE, a framework that enables context-aware adaptation by representing primitive caregiving skills as interaction templates whose execution is reshaped online. $E^2$-CARE represents the environment, the robot, and the human within a unified 3D dynamic scene graph that models these interaction contexts explicitly, and synthesizes task-specific constraints to govern how each skill is executed. By enforcing these constraints at runtime, the same skill templates can be reused zero-shot and safely across diverse environments and robot embodiments. We evaluate $E^2$-CARE across four activities of daily living in hundreds of simulated household environments, including assistive home settings, and across diverse robot embodiments, and validate it through user studies on two caregiving tasks with two robots in various real-world environments. Results demonstrate consistent and successful adaptation across these environments and embodiments. Website: https://emprise.cs.cornell.edu/e2care

Problem

• physical caregiving robots
• embodiment
• environment adaptation
• human-robot interaction
• context-awareness

Innovation

• context-aware robotics
• embodiment adaptation
• dynamic scene graph
• interaction templates
• zero-shot transfer