For fragile individuals with motor disabilities or rehabilitation needs, promoting physical activity while ensuring safe support is crucial. In this context, the growing demand for personalized assistance has heightened interest in robotic devices capable of providing adaptive, physically compliant support during walking. This letter presents an innovative control architecture for a Walking Assistive Robot (I-WANDER), designed to aid mobility, provide stability, and prevent falls in individuals with gait difficulties. 15 healthy participants were asked to walk along diverse paths while using the proposed controller and a classical admittance controller (AC). First, we evaluated the prediction model, which significantly outperformed a Kalman-filter method from the literature (p-value $< $ 0.001). Mean trajectory errors were in the centimeter range, thus demonstrating its suitability for real-time control. Subsequently, we compared the combined LSTM-MPC architecture with the AC and found a significant reduction in energy consumption (p-value $< $ 0.001) and improvements in perceived user effort. Overall, the results demonstrate the potential of integrating data-based trajectory prediction with predictive control to infer user intent, enhance human-robot interaction, and improve motion efficiency in assistive walking scenarios.
A. Fortuna, M. Lorenzini, Elisa Motta et al.· IEEE Robotics and Automation...· 0 citations
Loop Closure Detection is a fundamental component of any SLAM system. By performing place recognition, a robot can correct accumulated drift errors arising from odometry uncertainties during the mapping process. Numerous techniques have been proposed in the literature to address this task under different sensor configurations, including RGB cameras and LiDAR. Among these, LiDAR-based SLAM has gained substantial attention due to its robustness in outdoor environments and its invariance to illumination changes. However, LiDAR sensors inherently provide less texture information compared to cameras, introducing additional challenges for loop closure detection. One of the most widely adopted approaches in LiDAR-based SLAM is Scan Context, recognized for its simplicity and effectiveness. This method has been successfully integrated into a broad range of applications and algorithms. Nevertheless, its simplicity can also lead to reduced robustness when no supplementary verification mechanisms are employed. In this work, we introduce Gaussian Scan Context, an enhancement to the original Scan Context that incorporates statistical analysis of the input point cloud. This approach accounts for the distribution of points within each context bin. Experimental results demonstrate that this enhancement improves both robustness and overall performance, as supported by various metrics.
Non-prehensile manipulation of freely moving objects on a mobile base represents a significant challenge in underactuated robotics. This paper presents a sim-to-real reinforcement learning pipeline for a Unitree Go2 robot tasked with balancing a free-rolling ping-pong ball on a board mounted on its trunk while maintaining stable posture or tracking commanded velocities. Built on Legged Gym and the Genesis simulation, the proposed framework augments standard quadrupedal locomotion with ball-aware observations, task-specific reward design, and curriculum learning for progressively harder balancing and locomotion regimes. To improve transfer, the method incorporates domain randomization, camera-rate-compatible ball observations that mimic asynchronous visual feedback, and deployment-oriented safeguards such as smooth startup action blending. The learned policies are evaluated through a three-stage pipeline: large-scale training in Genesis, sim-to-sim validation in MuJoCo, and deployment on a physical Unitree Go2 using vision-estimated board-frame ball states. Experimental results show that the proposed framework can achieve both standing ball balance and ball-balancing locomotion on hardware, while additional comparisons between PPO and SAC highlight a trade-off between nominal task performance and disturbance robustness. These results suggest that reinforcement learning, when combined with transfer-aware observation design and deployment mechanisms, provides a practical approach for dynamic ball-balancing control on quadruped robots.