Sara M. Cerqueira

Vitor Martins, Sara M. Cerqueira, Mercedes Balcells et al.

Work-Related Musculoskeletal Disorders continue to be a major challenge in industrial environments, leading to reduced workforce participation, increased healthcare costs, and long-term disability. This study introduces a human-sensitive robotic system aimed at reintegrating individuals with a history of musculoskeletal disorders into standard job roles, while simultaneously optimizing ergonomic conditions for the broader workforce. This research leverages reinforcement learning (RL) to develop a human-aware control strategy for collaborative robots, focusing on optimizing ergonomic conditions and preventing pain during task execution. Two RL approaches, Q-Learning and Deep Q-Network (DQN), were implemented and tested to personalize control strategies based on individual user characteristics. Although experimental results revealed a simulation-to-real gap, a fine-tuning phase successfully adapted the policies to real-world conditions. DQN outperformed Q-Learning by completing tasks faster while maintaining zero pain risk and safe ergonomic levels, achieving on average 38% shorter task completion times across all tested anthropometries. The structured testing protocol confirmed the system's adaptability to diverse human anthropometries, underscoring the potential of RL-driven cobots to enable safer, more inclusive workplaces.

Manuel Palermo, Sara Cerqueira, João André et al.

The use of wearable technology for posture monitoring has been expanding due to its low-intrusiveness and compliance with daily use requirements. However, there are still open challenges limiting its widespread use, especially when dealing with low-cost systems. Most solutions falls either into fully functioning commercial products with high costs, or ad-hoc solutions with lower performance. Moreover, there are few datasets available, from which complete and general solutions can be derived. This work presents 2 datasets, containing low-cost and high-end Magnetic, Angular Rate, and Gravity (MARG) sensor data respectively. It provides data for the analysis of the complete inertial pose pipeline, from raw measurements, to sensor-to-segment calibration, multi-sensor fusion, skeleton kinematics, to the complete human pose. Multiple trials were collected with 21 and 10 subjects respectively, performing 6 types of sequences (ranging from calibration, to daily-activities and random movements). It presents a high degree of variability and complex dynamics with almost complete range-of-motion, while containing common sources of error found on real conditions. This amounts to 3.5M samples, synchronized with a ground-truth inertial motion capture system at 60hz. A simple end-to-end inertial pose method was briefly described and used to validate the quality of the data in both acquisitions. This database may contribute to assess, benchmark and develop novel algorithms for each of the pipelines' processing steps, with applications in classic or data-driven inertial pose estimation algorithms, human movement understanding and forecasting and ergonomic assessment in industrial or rehabilitation settings. All the data is freely available on an online database and accompanied with code to process and analyze the complete data pipeline.