Victor Paiva
Papers
2
Total Citations
4
H-Index
2
About
Victor Paiva is a rising researcher at the intersection of robotics, machine learning, and structural mechanics, with a focus on novel actuation and deployable systems. His work centers on two key areas: intelligent control of cable-driven robots and the design of tensegrity-based mechanisms. In his 2023 paper, Paiva pioneered the use of reinforcement learning—specifically PPO, SAC, and TD3 algorithms—to control a cable-driven SCARA robot, demonstrating how neural networks can replace traditional controllers for complex, flexible manipulators. This work, already garnering 2 citations, opens new pathways for adaptive, learning-based robotics in unstructured environments. More recently, his 2024 study on form-finding methods for deployable tensegrity arms introduced a novel approach to inverse kinematics, enabling precise motion planning for lightweight, collapsible structures. While early in his career, Paiva’s contributions are notable for bridging theoretical control methods with practical robotic applications, promising significant impact in fields like space exploration and disaster response where adaptable, cable-driven systems are critical.
Research Focus
Key Achievements
Top Papers
- 1
- 2