Henry Williams

About

Henry Williams is a robotics and agricultural automation researcher whose work sits at the intersection of computer vision, machine learning, and precision horticulture. Based in New Zealand, Williams has made landmark contributions to the development of autonomous agricultural robots, with a particular focus on kiwifruit production — a cornerstone of New Zealand's agricultural economy. His most celebrated work, "Robotic kiwifruit harvesting using machine vision, convolutional neural networks, and robotic arms" (2019), has amassed over 330 citations and established a foundational framework for deploying deep learning in real-world orchard environments. Complementing this, his research into autonomous kiwifruit pollination — addressing the alarming global decline of natural pollinators — has demonstrated that robots can effectively target and pollinate individual flowers with commercial viability, work collectively cited nearly 140 times across multiple studies. Williams has since extended his expertise to robotic grapevine pruning and reinforcement learning for dexterous manipulation, reflecting a broader vision for intelligent agricultural systems. His earlier work in adaptive path planning and multi-platform SLAM further underscores his versatility across core robotics challenges. For students exploring agricultural robotics or applied AI, Williams represents a compelling example of research driven by real-world necessity and measurable societal impact.

Research Focus

Key Achievements

Top Papers

1. 1
   Robotic kiwifruit harvesting using machine vision, convolutional neural networks, and robotic arms

   330 citations · 2019
2. 2
   Improvements to and large‐scale evaluation of a robotic kiwifruit harvester

   109 citations · 2019
3. 3
   Autonomous pollination of individual kiwifruit flowers: Toward a robotic kiwifruit pollinator

   96 citations · 2019
4. 4
   Modelling wine grapevines for autonomous robotic cane pruning

   31 citations · 2023
5. 5
   Emotion inspired adaptive robotic path planning

   19 citations · 2015
6. 6
   Learned Action SLAM: Sharing SLAM through learned path planning information between heterogeneous robotic platforms

   17 citations · 2016
7. 7
   Evaluating the Quality of Kiwifruit Pollinated with an Autonomous Robot

   16 citations · 2021
8. 8
   Comparison of Model-Based and Model-Free Reinforcement Learning for Real-World Dexterous Robotic Manipulation Tasks

   15 citations · 2023
9. 9
   Robotic Pollination - Targeting kiwifruit flowers for commercial application

   15 citations · 2017
10. 10
    Deep Neural Network Based Real-time Kiwi Fruit Flower Detection in an\n Orchard Environment

    12 citations · 2020

Key Collaborators

Contact & Links