Cameron Haigh

About

Cameron Haigh is a robotics and artificial intelligence researcher whose work spans reinforcement learning, robotic manipulation, and multi-agent swarm systems. He is perhaps best known for his contributions to real-world robotic reinforcement learning, particularly his development of counterfactual perception as prediction — a method that encodes action-oriented visual observations as learned "what if" queries derived from prior experience. This approach tackles one of the field's most persistent challenges: bridging the gap between simulation and practical deployment. His 2020 and 2022 papers on this topic, which together have attracted 14 citations, extend the framework to multimodal sensory inputs combining vision and force feedback for contact-rich manipulation tasks. More recently, Haigh has broadened his research into autonomous aerial systems and swarm robotics, contributing a probabilistic framework for missing-person search operations in complex urban environments and a novel method for restoring lost connectivity within robotic swarms — both published in 2024 and already accumulating citations. Across his body of work, Haigh demonstrates a consistent drive to make autonomous robotic systems more robust, adaptive, and practically deployable in unpredictable real-world conditions.

Research Focus

Key Achievements

Top Papers

1. 1
   Offline Learning of Counterfactual Perception as Prediction for Real-World Robotic Reinforcement Learning.

   9 citations · 2020
2. 2
   Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning

   5 citations · 2022
3. 3
   An Aerial Robotic Missing-Person Search in Urban Settings—A Probabilistic Approach

   3 citations · 2024
4. 4
   Restoring Connectivity in Robotic Swarms – A Probabilistic Approach

   3 citations · 2024

Key Collaborators

Contact & Links