Claudio Coppola

Claudio Coppola

Robotics And Machine Learning Scientist

Senior Research Engineer @ Thehumanoid.ai

Biography

Claudio Coppola is an artificial intelligence and robotics expert with strong academic credentials and industry experience. He specializes in applying advanced machine learning techniques to enable more intelligent robot systems.

Claudio obtained his PhD in Robotics from the University of Lincoln in 2018, where his doctoral research focused on human activity understanding to assist robots in indoor environments. He also holds a Master’s degree cum laude in Computer Engineering from the University of Naples Federico II in Italy. His work has led to numerous publications in leading journals and conferences like ICRA, IROS and IJSR.

During his experience as Applied Scientist at Amazon Transportation Services. Claudio has developed cutting-edge machine learning solutions for forecasting and pricing optimization. Previously at Queen Mary University of London, he researched robot learning for manufacturing automation. His work on tactile perception, teleoperation and learning from demonstrations aimed to enable adaptable industrial robots. With his technical expertise and passion for AI robotics, Claudio is an asset in initiatives fusing intelligent systems with automation.

Interests
  • Robot-learning
  • Human-Activity-Recognition
  • Machine-Learning
  • Time Series Forecasting
  • Robotic-Perception
Education
  • PhD in Robotics, 2018

    University of Lincoln

  • MSc in Computer Science Engineering, 2013

    Universitá degli studi di Napoli Federico II

  • BSc in Computer Science Engineering, 2011

    Universitá degli studi di Napoli Federico II

Experience

 
 
 
 
 
HumaNoid
Senior Research Engineer
August 2024 – Present London, UK
Research Engineer for Manipulation
 
 
 
 
 
BrainStation
Lead Instructor
November 2023 – Present London, UK

Lead Instructor for the AI and Data Science courses.

  • Delivered the Course material to professionals interested in changing their career towards data oriented and AI-dependant roles.
  • Advised students on their final project, objectives, and data choices.
 
 
 
 
 
Amazon
Applied Scientist
Amazon
July 2022 – August 2024 London, UK
Scoped, developed, and deployed cost estimation and volume forecasting solutions for the Amazon Transportation Services Less-Than-Truckload external facing product working in direct contact with customers at all the stages of development.
 
 
 
 
 
Queen Mary University of London
Postdoctoral Researcher
May 2019 – June 2022 London, UK
  • Performed reseach and supported PhD and Master students as member of the Advanced Robotics Queen-Mary (ARQ) Team.
  • Contributed to and Coordinated the work of PhD/MSc students for the EPSRC MAN3 Project, involving Shadow Robotics, Ocado and Google Deepmind.
  • Conducted research on learning by demonstration for robot manipulation by building a teleoperation platform and a demonstration segmentation system.
 
 
 
 
 
Entrepreneur First
LD11 Cohort Member
October 2018 – January 2019 London, UK
Took the role of CTO cooperating at the ideation of the start-up, public speaking, customer and product development and market analysis.
 
 
 
 
 
Buzzoole
Data Scientist
April 2018 – September 2018 Naples, Italy
  • Led the data science team, worked on several Machine Learning Projects central to raise $8.9M funding for the company to improve the analytics product
  • Object Detection in Social Media Images. This project helped to provide analytics about influencer topics to the company platform.
  • Fake Influencer Detection. This project tried to detect fake accounts and accounts using fake influencers to boost their metrics.
 
 
 
 
 
University of Lincoln
Research Associate
January 2017 – June 2018 Lincoln, UK
  • Developed state-of-the-art Human Activity Recognition and Re-identification models used in the EU H2020 research projects ENRICHME and FLOBOT.
  • Teaching Assistant for courses of Artificial Intelligence and Robotics.
 
 
 
 
 
KPMG Advisory
Business Intelligence Consultant
January 2014 – June 2014 Rome, Italy
  • Automated daily BI maintenance tasks with a speed-up above 90% and developed SQL queries to generate BI reports.

Accomplish­ments

Deep Reinforcement Learning Nanodegree
See certificate
Award to a group of excellent international researchers from the field of AI and grow our network of current fellows and alumni.
See certificate
Award of 2k for Postdocs working in AI
Coursera
Machine Learning
See certificate

Projects

.js-id-reinforcement-learning
Adversarial Agents with Reinforcement Learning
Reinforcement Learning algorithm to train tennis playing agents.
Adversarial Agents with Reinforcement Learning
Continuous Control with Reinforcement Learning
Reinforcement Learning algorithm to control a 2 jointed robot.
Continuous Control with Reinforcement Learning
CRISP Teleoperated Fruit Picking Dataset
Dataset containing the demonstration data collected with a teleoperation system. The CRISP teleoperated fruit picking dataset contains real-world teleoperated demonstration recordings of teleoperated grasping and manipulation sequences. The dataset offers recordings of RGB-D, Tactile and kinematic data collected during fruit pick-and-place tasks. Our items are placed in the workspace as single or as a clutter to simulate real-world food manufacturing scenarios.
CRISP Teleoperated Fruit Picking Dataset
Navigation Agent with Reinforcement Learning
Reinforcement Learning algorithm to train navigation agents.
Navigation Agent with Reinforcement Learning
UoL 3D Continuous Social Activity Dataset
Dataset is composed of 20 long RGB-D videos. Each video provides RGB-D images and tracked skeleton of different social and individual activities performed by two people.
UoL 3D Continuous Social Activity Dataset
UoL 3D Social Interaction Dataset
Dataset of 10 episodes containing a sequence of individual/social interactions in an indoor environment.
UoL 3D Social Interaction Dataset
Learning Temporal Context for activity recognition
Experiments for the ECAI 2016 publication. The experiments show different approaches for learning spatio-temporal context for indoor activity recognition.
Learning Temporal Context for activity recognition
ISR-UoL 3D Social Activity Dataset
This is a social interaction dataset between two subjects. This dataset consists of RGB and depth images, and tracked skeleton data (i.e. joints 3D coordinates and rotations) acquired by an RGB-D sensor.
ISR-UoL 3D Social Activity Dataset

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). Learning Decoupled Multi-touch Force Estimation, Localization and Stretch for Soft Capacitive E-skin. IEEE/RSJ International Conference of Robotics and Automation (ICRA) environment.

Cite

(2022). The CORSMAL benchmark for the prediction of the properties of containers. IEEE Access.

Cite

(2021). Discovering stable robot grasps for unknown objects in presence of uncertainty using bayesian models. Annual Conference Towards Autonomous Robotic Systems.

Cite Video

(2021). Filling Mass Estimation Using Multi-modal Observations of Human-Robot Handovers. Pattern Recognition. ICPR International Workshops and Challenges.

Cite Code

(2021). Multi-modal estimation of the properties of containers and their content: survey and evaluation. IEEE TRANSACTIONS ON MULTIMEDIA.

Cite

Contact

Hi Feel Free to send me an email!