Papers
8
Total Citations
107
H-Index
4
About
Justin Ting is a researcher at the forefront of neuromorphic computing, bio-inspired robotics, and edge AI, with a particular focus on enabling intelligent, energy-efficient locomotion and learning in autonomous systems. His most cited work, a 2018 paper on a time-domain mixed-signal neuromorphic accelerator (44 citations), demonstrated a remarkable 1.25-pJ/MAC energy efficiency for reinforcement learning in mobile robots — a landmark contribution to ultra-low-power hardware design for autonomous systems. Building on this foundation, Ting has pioneered end-to-end spiking neural network (SNN) platforms that integrate event-based vision sensors with central pattern generation, bridging the gap between biological locomotion principles and practical robotic deployment. His recurring focus on hexapod robot locomotion — addressed across multiple papers totaling over 25 additional citations — showcases his commitment to solving real-world constraints of energy, adaptability, and online learning. More recently, his HiPER framework explores hierarchical processing for learning-based model predictive control, signaling a broadening research trajectory. With over 100 cumulative citations, Ting's work offers invaluable contributions to researchers seeking biologically plausible, computationally lean solutions for next-generation edge robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8