Imitation learning (IL) has fundamentally transformed the field of legged robot locomotion, removing the dependence on hand-engineered reward functions. Since 2019, this area of research has progressed rapidly, from simple motion-capture replication to the generation of sophisticated policies using diffusion models. This survey offers a comprehensive analysis of 35 pivotal research works, using a structured six-dimensional framework to investigate advancements using quadrupedal and humanoid platforms. The review also pinpoints significant challenges related to deployment and outlines new research directions. A key finding from the survey indicates that behavior cloning is utilized in almost half of the analyzed studies. Moreover, data generated through model-predictive control (MPC) now represents the most frequently used training data source for advanced imitation learning systems.
Introduction:As robotic technologies become increasingly integrated into care settings, it is critical to assess their impact within the complexity of real-world contexts. This exploratory study examines the introduction of a robot cat for children with Autism Spectrum Disorder (ASD) in a specialist dental care unit. Children with ASD often face challenges in dental care, including anxiety, sensory sensitivities, and difficulty with collaboration. The study investigates if a robot cat can provide psychosocial support to the patients. Methods:Ten patients, aged 5-10, participated in the 12-months study, each undergoing one baseline session without the robot and 3-5 subsequent visits with the robot, yielding 37 sessions of video data. Results:Reflexive thematic analysis revealed three key themes: the robot cat can enhance training and treatment, robot cats can serve as a beneficial but a non-essential tool, and robot cats can sometimes hinder progress in training and treatment. These findings highlight significant individual variation in how the robot was experienced, shaped by context, timing, and emotional state. The robot's role was not universally positive or passive; its effectiveness depended on how it was integrated into personalised care strategies by the dental hygienist, guardians, and the patients themselves. Discussion:This study underscores the importance of tailoring technological interventions in care, advocating for cautious, context-sensitive use rather than one-size-fits-all solutions. Future work should further explore adaptive, individualised deployment.
For autonomous mobile robots to operate effectively in human environments, navigation must extend beyond obstacle avoidance to incorporate social awareness. Safe and fluid interaction in shared spaces requires the ability to interpret human motion and adapt to social norms—an area that is being reshaped by advances in learning-based methods. This review examines recent progress in learning-based social navigation methods that deal with the complexities of human-robot coexistence. We introduce a taxonomy of navigation methods and analyze core system components, including realistic training environments and objectives that promote socially compliant behavior. We conduct a comprehensive benchmark of existing frameworks in challenging crowd scenarios, showing their advantages and shortcomings, while providing critical insights into the architectural choices that impact performance. We find that many learning-based approaches outperform model-based methods in realistic coordination scenarios such as navigating doorways. A key highlight is the end-to-end models, which achieve strong performance by directly planning from raw sensor input, enabling more efficient and adaptive navigation. This review also maps current trends and outlines ongoing challenges, offering a strategic roadmap for future research. We emphasize the need for models that accurately anticipate human movement, training environments that realistically simulate crowded spaces, and evaluation methods that capture real-world complexity. Advancing these areas will help overcome current limitations and move social navigation systems closer to safe, reliable deployment in everyday environments. Additional resources are available at: https://socialnavigation.github.io.
Robotic grippers are widely utilized in industrial manufacturing, but object slippage during assembly poses challenges, including potential damage, delays, and increased costs. Therefore, early slip detection is crucial for efficient manufacturing operations. Piezoelectric tactile sensors using polyvinylidene fluoride (PVDF) have been developed to detect vibrations. Nevertheless, the development of such sensors with a simple structure and lower fabrication cost, continues to be a challenging task. The analysis on the effect of the thicknesses of soft body layers that attached to sensing elements on the slip sensor’s performance has yet been discussed. In this project, a simple-structured and low-cost design of a flexible piezoelectric tactile sensor based on PVDF to estimate slip using robotic gripper is presented. The effect of different thicknesses of soft body layer made of silicone rubber and the sensor’s performance in detecting slip is discussed. A PVDF-based sensor is attached to soft body layer that is incorporated into a robotic gripper. Experimental results demonstrate that sensor sensitivity increases with lower soft body layer thickness. Additionally, the sensor’s signal amplitude increases with object load, indicating slip intensity. This advancement addresses challenges in fabricating simple structures and cost-effective piezoelectric sensors which enhance robotic gripper functionality in industrial applications.
Parkinson’s Disease is a progressively advancing neurological condition. Its severity is evaluated by utilizing the Hoehn and Yahr staging scale. Such assessments may be inconsistent, are more time-consuming, and expensive for patients. To address these shortcomings, this article introduces a machine learning-based gait classification system to assist doctors in identifying the stages of Parkinson’s disease. This study utilizes two open-access benchmark datasets from PhysioNet and Figshare to assess ground reaction force collected from patients diagnosed with Parkinson’s Disease. This study presents experiments conducted using machine learning algorithms namely Decision Tree, Random Forest, Extreme Gradient Boost, and Light Gradient Boosting Machine classification algorithms to predict severity of Parkinson’s Disease. Among all the four algorithms, Light Gradient Boosting Machine classification algorithm have proven its supremacy. It gave an accuracy of 98.25%, Precision of 98.35%, Recall of 98.25%, and F1 Score of 98% for dataset 1. The performance of the algorithm slightly declines on dataset 2. It reports accuracy of 85%, Precision of 95%, Recall of 85% and F1 Score of 89% for dataset 2. Furthermore, this study used Explainable Artificial Intelligence to display the LightGBM classifier’s classification pathways for Parkinson’s disease severity prediction using Hoehn and Yahr staging on the scale from 0 to 5. This is helps the health experts in decision making. This work provides automated assistance to doctors for the rapid screening of Parkinson’s disease patients based on disease severity. This work leaves a scope for integrating wearable sensors and developing real-time monitoring system for screening of Parkinson’s Disease patients.
