This paper describes a proposed robotic artwork for the MOCO 2024 conference. Real Robot Dance Challenge is a human-robot art installation that investigates both live human-robot interactions as well as human movement embedded in online videos as sources for the robot's movement. Dance is extremely challenging for a robot in terms of movement goals. Compared to typical industrial robot approaches, actions may have a comparative excess expenditure of energy, and style and expressivity becoming more important than accuracy and control. This work draws on the popular trend of dance challenges as seen on platforms such as Tik Tok [1]. The short format dances, often 10 – 30 seconds long, are choreographed with the intention of showcasing skills as well as challenging others to reinterpret the dance, often done with individual stylistic changes. RRDC challenges the robot to reinterpret the movement of human movers interacting live as well as dances contained in online videos. The artwork leverages the unity game engine as a mediating platform for the robot to access human movement and repurpose it for its own body. This allows the robot's movement to be procured from multiple sources. The unity environment can also be used to connect robots of different morphologies to the movement sources enabling flexibility in the engagement between human and robot. The robot moves beyond the control of programmed actions, able to respond with interpretations of the movement offered to it.
Labor shortages and aging populations are straining hospital systems globally, prompting interest in humanoid robots as a viable technology solution for healthcare support. This paper presents a proof-of-concept deployment of a Unitree G1 humanoid robot using advanced SLAM with multi-modal sensors (LiDAR, depth cameras) for reliable navigation in dynamic hospital-like environments. Unlike conventional approaches that model humans solely as obstacles to avoid, our system implements human-aware navigation. Respecting proxemics, social context, and malleable spatial boundaries to treat people as collaborative partners, enabling safe, legible co-navigation in crowded wards and corridors. By demonstrating autonomous, purposeful movement for logistics and patient-support tasks, this research illustrates a pathway to augment healthcare delivery, worker support, and patient care outcomes through adaptable, human-centered robotics.
Echocardiography is a key imaging modality for cardiac assessment but remains highly operator-dependent, and access to trained sonographers is limited in underserved settings. Teleoperated robotic echocardiography has been proposed as a solution; however, clinical studies report longer examination times than manual procedures, increasing diagnostic delays and operator workload. Automating non-expert tasks, such as automatically moving the probe to an ideal starting pose, offers a pathway to reduce this burden. Prior vision- and depth-based approaches to estimate an initial probe pose are sensitive to lighting, texture, and anatomical variability. We propose a robot-mounted 2D LiDAR-based approach that reconstructs the chest surface in 3D and estimates the initial probe pose automatically. To the best of our knowledge, this is the first demonstration of robot-mounted 2D LiDAR used for 3D reconstruction of a human body surface. Through plane-based extrinsic calibration, the transformation between the LiDAR and robot base frames was estimated with an overall root mean square (RMS) residual of 1.8 mm and rotational uncertainty below 0.2°. The chest front surface, reconstructed from two linear LiDAR sweeps, was aligned with non-rigid templates to identify an initial probe pose. A mannequin-based study assessing reconstruction accuracy showed mean surface errors of 2.78 +/- 0.21 mm. Human trials (N=5) evaluating the proposed approach found probe initial points typically 20-30 mm from the clinically defined initial point, while the variation across repeated trials on the same subject was less than 4 mm.
Learning from Demonstration (LfD) enables robots to acquire manipulation skills by observing human actions. However, existing methods often face challenges such as high computational cost, limited generalizability, and a loss of key interaction details. This study presents a compact representation for interaction recognition in LfD that encodes human–object interactions using 2D wrist trajectories and 3D object poses. A lightweight extraction pipeline combines MediaPipe-based wrist tracking with FoundationPose-based 6-DoF object estimation to obtain these trajectories directly from RGB-D video without specialized sensors or heavy preprocessing. Experiments on the GRAB and FPHA datasets show that the representation effectively captures task-relevant interactions, achieving 94.6% accuracy on GRAB and 96.0% on FPHA with well-calibrated probability predictions. Both Bidirectional Long Short-Term Memory (Bi-LSTM) with attention and Transformer architectures deliver consistent performance, confirming robustness and generalizability. The method achieves sub-second inference, a memory footprint under 1 GB, and reliable operation on both GPU and CPU platforms, enabling deployment on edge devices such as NVIDIA Jetson. By bridging pose-based and object-centric paradigms, this approach offers a compact and efficient foundation for scalable robot learning while preserving essential spatiotemporal dynamics.