Untitled

Funder

Organizational Unit

Publications

Energy Efficiency Analysis of Differential and Omnidirectional Robotic Platforms: A Comparative Study

Publication . Chellal, Arezki Abderrahim; Braun, João; Junior, Luciano Bonzatto; Faria, Milena; Kalbermatter, Rebeca B.; Gonçalves, José; Costa, Paulo Gomes da; Lima, José

As robots have limited power sources. Energy optimization is essential to ensure an extension for their operating periods without needing to be recharged, thus maximizing their uptime and minimizing their running costs. This paper compares the energy consumption of different mobile robotic platforms, including differential, omnidirectional 3-wheel, omnidirectional 4-wheel, and Mecanum platforms. The comparison is based on the RobotAtFactory 4.0 competition that typically takes place during the Portuguese Robotics Open. The energy consumption from the batteries for each platform is recorded and compared. The experiments were conducted in a validated simulation environment with dynamic and friction models to ensure that the platforms operated at similar speeds and accelerations and through a 5200 mAh battery simulation. Overall, this study provides valuable information on the energy consumption of different mobile robotic platforms. Among other findings, differential robots are the most energy-efficient robots, while 4-wheel omnidirectional robots may offer a good balance between energy efficiency and maneuverability.

2024Conference paper

Restricted access

Assessing the Reliability of AI-Based Angle Detection for Shoulder and Elbow Rehabilitation

Publication . Klein, Luan C.; Chellal, Arezki Abderrahim; Grilo, Vinicius F.S.B.; Gonçalves, José; Pacheco, Maria F.; Fernandes, Florbela P.; Monteiro, Fernando C.; Lima, José

Angle assessment is crucial in rehabilitation and significantly influences physiotherapists’ decision-making. Although visual inspection is commonly used, it is known to be approximate. This work aims to be a preliminary study about using the AI image-based to assess upper limb joint angles. Two main frameworks were evaluated: MediaPipe and Yolo v7. The study was performed with 28 participants performing four upper limb movements. The results showed that Yolo v7 achieved greater estimation accuracy than Mediapipe, with MAEs of around 5◦ and 17◦, respectively. However, even with better results, Yolo v7 showed some limitations, including the point of detection in only a 2D plane, the higher computational power required to enable detection, and the difficulty of performing movements requiring more than one degree of Freedom (DOF). Nevertheless, this study highlights the detection capabilities of AI approaches, showing be a promising approach for measuring angles in rehabilitation activities, representing a cost-effective and easyto- implement solution.

2024Conference paper

Restricted access