Max Robotics — Global Service Robot Directory + US Certification

About

Abhik Singla is a robotics researcher whose work sits at the intersection of deep reinforcement learning and autonomous locomotion, tackling two of the most challenging domains in robotics: agile flight and legged locomotion. His most cited work, "Memory-Based Deep Reinforcement Learning for Obstacle Avoidance in UAV With Limited Environment Knowledge" (16 citations), introduces a novel method enabling quadrotors equipped with only a monocular camera to navigate and avoid collisions in completely unknown indoor environments—a significant leap over ground-based systems. In the realm of legged robotics, Singla has made foundational contributions to quadrupedal walking. His paper "Trajectory based Deep Policy Search for Quadrupedal Walking" (8 citations) reimagines policy optimization by determining optimal strategies for entire walking cycles rather than individual time steps. Further, his work on "Learning Active Spine Behaviors for Dynamic and Efficient Locomotion" (4 citations) provides a simulation framework to systematically study how spinal joint compliance and actuation can dramatically improve bounding performance in robots like Stoch 2. Through these contributions, Singla demonstrates a rare ability to bridge memory-based learning for aerial vehicles with bio-inspired motion primitives for ground robots, establishing himself as a versatile innovator in autonomous systems.