Placeholder image for staff profiles

Pete Blacker

Postgraduate Research Student

My research project

My publications


Nanjangud S, Blacker P, Bandyopadhyay S, Gao Y (2018) Robotics and AI-Enabled On-Orbit Operations With Future Generation of Small Satellites,Proceedings of the IEEE106(3)pp. 429-439 Institute of Electrical and Electronics Engineers (IEEE)
The low-cost and short-lead time of small satellites has led to their use in science-based missions, earth observation, and interplanetary missions. Today, they are also key instruments in orchestrating technological demonstrations for on-orbit operations (O3) such as inspection and spacecraft servicing with planned roles in active debris removal and on-orbit assembly. This paper provides an overview of the robotics and autonomous systems (RASs) technologies that enable robotic O3 on smallsat platforms. Major RAS topics such as sensing & perception, guidance, navigation & control (GN&C) microgravity mobility and mobile manipulation, and autonomy are discussed from the perspective of relevant past and planned missions.
Blacker P., Bridges C. P., Hadfield S. (2019) Rapid Prototyping of Deep Learning Models on Radiation Hardened CPUs,Proceedings of the 13th NASA/ESA Conference on Adaptive Hardware and Systems (AHS 2019) Institute of Electrical and Electronics Engineers (IEEE)

Interest is increasing in the use of neural networks and deep-learning for on-board processing tasks in the space industry [1]. However development has lagged behind terrestrial applications for several reasons: space qualified computers have significantly less processing power than their terrestrial equivalents, reliability requirements are more stringent than the majority of applications deep-learning is being used for. The long requirements, design and qualification cycles in much of the space industry slows adoption of recent developments.

GPUs are the first hardware choice for implementing neural networks on terrestrial computers, however no radiation hardened equivalent parts are currently available. Field Programmable Gate Array devices are capable of efficiently implementing neural networks and radiation hardened parts are available, however the process to deploy and validate an inference network is non-trivial and robust tools that automate the process are not available.

We present an open source tool chain that can automatically deploy a trained inference network from the TensorFlow framework directly to the LEON 3, and an industrial case study of the design process used to train and optimise a deep-learning model for this processor. This does not directly change the three challenges described above however it greatly accelerates prototyping and analysis of neural network solutions, allowing these options to be more easily considered than is currently possible.

Future improvements to the tools are identified along with a summary of some of the obstacles to using neural networks and potential solutions to these in the future.

Nanjangud Angadh, Blacker Peter C., Young Alex, Saaj Chakravarthini M., Underwood Craig I., Eckersley Steve, Sweeting Martin, Bianco Paolo (2019) Robotic architectures for the on-orbit assembly of large space telescopes,Proceedings of the Advanced Space Technologies in Robotics and Automation (ASTRA 2019) symposium European Space Agency (ESA)
Space telescopes are our ?eyes in the sky? that enable unprecedented astronomy missions and also permit Earth observation integral to science and national security. On account of the increased spatial resolution, spectral coverage, and signal-to-noise ratio, there is a constant clamour for larger aperture telescopes by the science and surveillance communities. This paper addresses a 25 m modular telescope operating in the visible wavelengths of the electromagnetic spectrum; such a telescope located at geostationary Earth orbit would permit 1 m spatial resolution of a location on Earth. Specifically, it discusses the requirements and architectural options for a robotic assembly system, called Robotic Agent for Space Telescope Assembly (RASTA). Aspects of a first-order design and initial laboratory test-bed developments are also presented.