Alexander Broad

Northwestern University, Boston Dynamics (United States)

Papers

Total Citations

130

H-Index

About

Alexander Broad is a leading researcher at the intersection of assistive robotics, human-robot interaction, and machine learning. His work focuses on developing intelligent robotic systems that can collaborate seamlessly with humans, particularly individuals with motor impairments. Broad’s major contributions include pioneering shared autonomy frameworks that combine model-based and model-free reinforcement learning, enabling robots to learn and adapt more efficiently. His highly cited 2015 paper (67 citations) introduced a Body-Machine Interface for assistive manipulation, allowing users to control robotic arms for daily tasks like grasping and feeding. Broad also advanced real-time natural language correction interfaces (25 citations), enabling users to verbally guide and correct robot behavior during operation. His path planning research under interface-based constraints (8 citations) addresses the critical challenge of ensuring robot motion aligns with human control limitations. With over 130 total citations, Broad’s work is foundational for developing safe, intuitive, and adaptive assistive robots. His hybrid control approach (2022, 30 citations) represents a significant step toward robots that can leverage both predictive models and experiential learning, promising more capable and responsive assistive technologies for real-world home environments.