Terence D. Sanger

About

Terence D. Sanger is a pioneering researcher at the intersection of neural control, robotics, and rehabilitation engineering. His work fundamentally advances how machines learn from and interact with biological systems, particularly in high-dimensional and uncertain environments. Sanger’s early contributions include a tree-structured adaptive network for function approximation in high-dimensional spaces (129 citations) and neural network learning control for robot manipulators using gradually increasing task difficulty (112 citations), establishing foundational methods for efficient motor learning. He introduced the theory of risk-aware control (34 citations), which redefines human movement as governed by risk estimates rather than traditional optimal control, offering a new paradigm for understanding motor flexibility and robustness. In rehabilitation, Sanger developed a robotic forearm orthosis using soft fabric-based helical actuators (52 citations) and validated synergy-based myocontrol for multi-degree-of-freedom robotic arms (63 citations), demonstrating practical applications for assistive devices. His neuromorphic-meets-neuromechanics work (35 and 30 citations) faithfully implements spinal circuitry and fusimotor drive, creating realistic robotic systems that emulate biological sensorimotor function. Sanger’s research bridges theory and application, profoundly impacting neural engineering, robotics, and clinical rehabilitation.

Research Focus

Key Achievements

Top Papers

1. 1
   A tree-structured adaptive network for function approximation in high-dimensional spaces

   129 citations · 1991
2. 2
   Neural network learning control of robot manipulators using gradually increasing task difficulty

   112 citations · 1994
3. 3
   Robustness and Reliability of Synergy-Based Myocontrol of a Multiple Degree of Freedom Robotic Arm

   63 citations · 2015
4. 4
   A robotic forearm orthosis using soft fabric-based helical actuators

   52 citations · 2019
5. 5
   Neuromorphic meets neuromechanics, part I: the methodology and implementation

   35 citations · 2017
6. 6
   Risk-Aware Control

   34 citations · 2014
7. 7
   Neuromorphic meets neuromechanics, part II: the role of fusimotor drive

   30 citations · 2017
8. 8
   Emulated muscle spindle and spiking afferents validates VLSI neuromorphic hardware as a testbed for sensorimotor function and disease

   24 citations · 2014
9. 9
   Optimal unsupervised motor learning for dimensionality reduction of nonlinear control systems

   16 citations · 1994
10. 10
    OPTIMAL HIDDEN UNITS FOR TWO-LAYER NONLINEAR FEEDFORWARD NEURAL NETWORKS

    14 citations · 1991

Key Collaborators

Contact & Links