Embodied Human Simulation for Interactive Robotics

Demonstration

Demonstrations of the coupled human-robot model with interactive simulation framework.

Video 1. Human Walking with Exoskeleton

The co-optimization pipeline applied to a wearable exoskeleton, the human policy is trained and applied to robotics optimization.

Video 2. Human–G1 Collaborative Carrying

The framework's scalability to diverse interactive robotics, illustrated by a human-humanoid collaborative table-carrying task.

Overview

Physical interactive robotics, ranging from wearable devices to collaborative humanoid robots, require close coordination between mechanical design and control. However, evaluating interactive dynamics is challenging due to complex human biomechanics and motor responses. Traditional experiments rely on indirect metrics without measuring human internal states, such as muscle forces or joint loads. To address this issue, we develop a scalable simulation-based framework for the quantitative analysis of physical human-robot interaction. At its core is a full-body musculoskeletal model serving as a predictive surrogate for the human dynamical system. Driven by a reinforcement learning controller, it generates adaptive, biomechanically constrained motor behaviors for interaction analysis. We employ a sequential training pipeline where the pre-trained human motion control policy acts as a consistent evaluator, making large-scale design space exploration computationally tractable. By simulating the coupled human-robot system, the framework provides access to internal biomechanical metrics, offering a systematic way to jointly optimize robot structural and control parameters. We demonstrate its capability in optimizing human-exoskeleton interactions, showing improved joint alignment and reduced contact forces. This work establishes embodied human simulation as a scalable paradigm for interactive robotics design.

Digital human simulation applied to exoskeleton optimization and collaborative manipulation

Figure 1. Demonstrations of the Digital Human Embodiment with interactive simulation framework. (a) The co-optimization pipeline applied to a wearable exoskeleton, the human policy is trained and applied to robotics optimization. (b) The framework's scalability to diverse interactive robotics, illustrated by a daily collaborative task with a humanoid robot.

Framework

A pretrained human motor policy evaluates each robot design in a coupled MuJoCo simulation. The measured interaction cost is returned to the optimizer, which proposes the next combination of controller gains and structural parameters.

Parameterized human-exoskeleton coupled simulation model

Figure 2. The human-exoskeleton coupled simulation model. (a) The full system, showing the MS-Human-700 model wearing the OpenExo exoskeleton. (b) A detailed view of the human-robot physical interface, where the adduction joint is passive to allow adaptation to natural leg abduction movement. (c) Illustration of the adjustable structural parameters in the interactive system. Local cuff adjustments correspond to vertical shifts at binding sites, while global assembly module adjustments modify the axis relative to attached human body segment through rotations and translations. The interactions were modeled with compliant elastic tendons elements (gray spheres) that connect the exoskeleton shell to the underlying human segment and transmit assistive forces.

Closed-loop framework for digital human simulation and robot optimization

Figure 3. Flowchart of the co-optimization loop. The optimization algorithm proposes a new set of exoskeleton parameters (control and structure). The human-robot coupled simulation is executed for several gait cycles with these parameters. The resulting motion and physiological data are used to evaluate the cost function. This cost is returned to the optimizer, which updates its internal model and proposes the next set of parameters to evaluate, iterating until convergence.

Human Policy Validation

The digital human must reproduce the intended motion and remain responsive to external interaction. We validate both its walking fidelity and its ability to recover from unexpected forces.

Simulated and reference joint angles during walking

Video 3. Human Walking

The learned full-body musculoskeletal policy tracks the walking motion evaluated in Figure 4.

Figure 4. Validation of the digital human's walking kinematics. The simulated joint angles (blue solid lines) are compared with the reference motion capture data (green dashed lines) for major joints. The shaded areas represent the standard deviation across 10 simulation trials with different initialization time steps, indicating high consistency.

Digital human recovering from external perturbations during walking

Video 4. Push Recovery

The learned human policy restores balance and gait after the perturbations analyzed in Figure 5.

Figure 5. Robustness evaluation of the learned walking policy against external perturbations. (a) The agent's dynamic recovery sequence after an impulsive force is applied to the pelvis, where the pink arrow visualizes the applied disturbance force. (b) Recovery time across a range of forward (positive) and backward (negative) forces. The red line shows the time required to recover the original kinematic trajectory, demonstrating a fast return to the intended motion. The shaded area represents the standard deviation over 10 randomly initialized trials.

Co-Optimization Results

The exoskeleton case study shows why control and physical structure should be designed together. Joint optimization improves the overall interaction objective and produces better alignment between robotic and biological joints.

Figure 6. Performance comparison of optimization strategies. The top three panels illustrate the average joint error, muscle force, and contact force during the co-optimization of controller and structure parameters across episodes, showcasing the improvements. The bottom panel compares the normalized minimum total cost achieved so far for three strategies: controller-only (blue), structure-only (green), and co-optimization (red). The co-optimization approach demonstrates significantly faster convergence and a lower final cost, highlighting the benefits of concurrently optimizing control and structure.

Human and exoskeleton joint-axis alignment before and after optimization

Figure 7. Enhanced human-robot joint axis alignment after co-optimization. The left column shows the shortest distance between the corresponding human and exoskeleton joint axes, while the right column shows the angle between them. Shaded areas represent the standard deviation across 10 simulation trials. The optimized parameters significantly reduce both distance and angular deviation, enabling more effective and comfortable force transmission.

Citation

@inproceedings{zuo2026embodied, title={Embodied Human Simulation for Quantitative Design and Analysis of Interactive Robotics}, author={Zuo, Chenhui and Xu, Jinhao and Vergnolle, Michael Qian and Sui, Yanan}, booktitle={2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, year={2026} }