Robotic assistance for human mobility could benefit care recipients and reduce caregiver burden during physically demanding tasks such as Sit-to-Stand (STS) and Lift-and-Transfer (L&T). Learning robot policies for these whole-body assistive tasks is challenging: real-world data collection for human-robot interaction is costly and safety-critical, making simulation an attractive alternative. Prior work, however, typically treats the human as static or minimally responsive and thus fails to capture the cooperative nature of mobility assistance. We present a simulation-based framework for learning whole-body assistive robot policies. At its core is a human policy trained with an adversarial motion prior that produces realistic care-recipient motion in response to the robot's actions. A human-adaptive scripted controller interacts with this policy to collect diverse robot demonstrations at scale. From these demonstrations, we train 3D diffusion policies that map segmented human point clouds and robot joint positions to whole-body actions for a mobile manipulator, without relying on privileged human state at deployment. The resulting robot policies successfully perform both STS and L&T assistance in simulation. Preliminary experiments further demonstrate sim-to-real transfer for STS after fine-tuning on a small amount of real-world data. Videos are available on our project page: https://rchi-lab.github.io/human-gen-mobility-assistance/
Figures & tables
Fig. 1: (Left) The bimanual mobile assistive robot platform used in this study. (Right) Sequence of STS assistance performed with the robot.
Fig. 2: Our training pipeline consists of three stages. (Left) We train a physics-based human policy via reinforcement learning, combining an Adversarial Motion Prior (AMP) for motion realism with latent conditioning to encourage diverse human behaviors. (Middle) Using the trained human policy, we simulate robot assistance with a human-adaptive scripted controller. Successful interactions are filtered and stored as robot demonstrations. (Right) We learn an assistive robot policy with a 3D diffusion-policy architecture using the collected demonstrations. At deployment, the policy predicts actions from human point clouds and robot joint positions without privileged human state information.
Fig. 3: Task setups and key interaction points for scripted robot demonstration collection in STS (upper row) and L&T (lower row).
Variant
Disc. Score ( ↑ )
Joint Angle Std. ( ↑ ) [ rad ]
AMP+Latent (Ours)
0.384±0.052
0.091
AMP-only
0.356 ± 0.053
0.030
Latent-only
0.002±0.010
0.141
Vanilla
0.003±0.008
0.048
TABLE I: Evaluation of generated human motions on STS.
Fig. 5: Representative successful evaluation rollouts of our learned policies for STS and L&T. For each task, the upper and lower sequences correspond to human body scales of 0.88× and 1.0× , respectively. The robot reaches the pre-lift configuration and completes the assistance in all examples.
Fig. 6: Representative failure rollouts of our learned policies. Top: in STS, the robot does not lift the human sufficiently high, leaving the human in a non-upright posture. Bottom: in L&T, the robot places its arms incorrectly, preventing the human from reaching the handle and being properly lifted. Red dashed boxes highlight the main failure regions.
Robot Policy Trained With
Pre-lift SR (%, ↑ )
Final SR (%, ↑ )
Mixed 1.0×,0.25× capability (Ours)
98.3±2.4
95.7±2.7
Single 1.0× capability
96.7±2.7
90.3±7.1
Single 0.25× capability
98.3±2.4
94.0±4.4
TABLE III: Ablation on human capability in STS robot policy training.
Fig. 7: The learned human models are not able to stand up independently. The top row shows a successful rollout with full robot assistance. The middle and bottom rows show the same rollout with assistance terminated at lift start and mid-lift, respectively. In both terminated conditions, the human fails to stand without sufficient robot assistance.
Fig. 8: Real-world deployment of the learned assistive robot policy. The fine-tuned policy assists a human participant in a real-world STS interaction.
Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China. · School of Nursing, The Hong Kong Polytechnic University, Hong Kong SAR, China. · School of Physics, Engineering and Technology, University of York, UK. +1