Papers

7

Total Citations

241

H-Index

5

About

Joseph McIntyre's research career bridges two seemingly distinct worlds: the precision of robotic control and the complexity of human motor coordination. His early work in the 1980s pioneered model-based robot learning, introducing algorithms that allowed robots to refine their movements through practice by using inverse models to process trajectory errors—a foundational contribution that earned over 158 citations for his 1986 paper. This work laid the groundwork for adaptive feedforward control in robotics, demonstrating how machines could learn from performance errors to improve positioning and trajectory following. More recently, McIntyre has turned his attention to understanding human movement, particularly the biomechanics and neural control of catching. His 2012 study on minimum jerk trajectories in 3D catching movements revealed how humans optimize speed and smoothness when intercepting a ball, while his work on the NEURARM platform—a bio-inspired robotic arm—models the antagonistic, non-linear actuation of human joints. By developing robotic systems that imitate human neuromuscular properties, McIntyre has created powerful tools for investigating motor control, showing how mechanical stiffness and neural oscillations may contribute to movement stability. His career exemplifies how robotics can illuminate human physiology.

Research Focus

Key Achievements

5
H-Index
7
Papers
241
Total Citations
34
Avg Citations/Paper
🏆 Most Cited Paper
Robot trajectory learning through practice
158 citations · 1986
📈 Most Prolific Year: 2008 (2 Papers)
🤝 Key Collaborators: 13
🏛 Institutions: Massachusetts Institute of Technology, Université Paris Cité, Centre National de la Recherche Scientifique

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
    Model-based robot learning
    16 citations · 1988
  6. 6
  7. 7

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago