↓Skip to main content
Raghav Mishra

Raghav Mishra

Roboticist, Mechatronic Engineer

I’m a Robotics PhD student at the Australian Centre for Robotics. My research spans robotics, control theory and machine learning. In particular, I work across topics like sampling-based control, generative AI, and space autonomy.

I did my Bachelors/Masters in Mechatronic Engineering at the University of Queensland. Previously, I’ve worked at Emesent as a Robotics Autonomy Engineer, making drones and legged robots for inspection and 3D mapping. I’ve also interned at CSIRO Robotics and Microsoft AutoML.

Publications

Diffusion policies in milliseconds, directly from the demonstration dataset and fast inference on a mobile CPU and inference-time neural diffusion policy editing to steer actions or add new demonstrations to the policy
Energy and Disturbance aware Pose Optimisation for Kinematically-Redundant Systems, applied on an UVMS Contact-Sensing Mission
Sahaj Mand, Raghav Mishra, Stefan Williams
Australasian Conference on Robotics and Automation (ACRA), 2026
We propose UVMS pose optimizer improves disturbance rejection capability and energy usage during a mission, without disrupting the primary task.
Raghav Mishra, Ian R. Manchester
IEEE International Conference on Robotics & Automation (ICRA), 2026
Constrained Model-Based Diffusion using interior-point inspired barrier functions to improve performance in highly constrained optimization without using computationally expensive projections.
Jack Naylor, Raghav Mishra, Nicholas H Barbara, and Donald G Dansereau
International Aeronautical Conference (IAC), 2025
An end-to-end differentiable simulation pipeline with orbital propagation and physically based rendering for on-orbit inspection operations to optimise inspection trajectories for image quality.
Appearance-Aware Trajectory Optimisation for On-Orbit Inspection
Raghav Mishra, Jack Naylor, Nicholas H Barbara, and Donald G Dansereau
International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS), 2024
Appearance-aware impulsive trajectory optimisation using differentiable Lambert problem solver, using Blender-in-the-loop as an appearance model and using gradient-based optimisation.
Cameron Coombe; James Brett; Raghav Mishra; Gary W. Delaney; David Howard
IEEE International Conference on Soft Robotics (RoboSoft), 2023
We augment a conventional universal gripper with a computer-controllled audio exciter to show it can improve holding strength. We build an automated test rig to allow large-scale data collection to explore the effects of active vibration.

Articles

What is the controllability matrix telling us?
·339 words·2 mins
Linear algebra perspectives on frequency transforms - Part 2
·1252 words·6 mins
Linear algebra perspectives on frequency transforms - Part 1
·1738 words·9 mins
What is Control theory?
·1639 words·8 mins
Why convolutions?
·1226 words·6 mins