Active Hackathon

DeepMind’s Progress Over The Years In Robotics

Backed by Alphabet, DeepMind’s progress has helped it hold the flag high in robotics over the past few years.
DeepMind Robotics

AI Research Lab DeepMind acquired and open-sourced MuJoCo, a rich and effective contact model. By open-sourcing Multi-Joint Dynamics with Contact (MuJoCo), DeepMind has given a major push to its robotics ambition.

This article will trace how DeepMind has been making consistent efforts in pushing the envelope in robotics.


Sign up for your weekly dose of what's up in emerging technology.

Deep reinforcement learning to training robots

In 2016, DeepMind researchers demonstrated how deep reinforcement learning can train real physical robots. The paper showed that deep Q-functions-based reinforcement learning algorithms can scale to complex 3D manipulation tasks and efficiently learn deep neural network policies. The authors further showed that the time to train the robots can be further reduced by algorithm parallelisation across multiple robots that asynchronously pool their policy updates. The proposed methodology can learn a variety of 3D manipulations skills in simulation and a door opening skill (often considered a complex task for robots to train on) without manually designed representations.

Producing Flexible Behaviours

In 2018, DeepMind published three major papers to demonstrate flexible and natural behaviours to reuse and adapt to solve tasks. The scientists trained agents with a variety of simulated bodies to perform activities like jumping, turning, and crouching across diverse terrains. The results showed that the agents develop these skills without receiving specific instructions.

Credit: DeepMind

Another paper demonstrated a method to train a policy network that imitates motion capture data of human behaviours to pre-learn skills like walking, getting up from the ground, turning, and running. These behaviours can then be tuned and repurposed to solve other tasks like climbing stairs and navigating through walled corridors.

The third paper produced a neural network architecture based on state of the art generative models. This research showed how this architecture is capable of learning relationships between different behaviours and imitating specific actions that are shown to it. After training, the systems could encode a single observed action and create a new novel movement.

Scaling data-driven robotics

DeepMind demonstrated a framework for data-driven robotics which uses a large dataset of recorded robot experience before scaling it to several tasks using a learned reward function. This framework can be applied to accomplish three different object manipulation tasks on a real robot platform. 

The scientists used a special form of human annotations as supervision to learn a reward function and demonstrate tasks with task-agnostic recorded experience. This helps in dealing with real-world tasks where the reward signal cannot be acquired directly.

The learned rewards and large dataset of experience derived from different tasks are used to learn robot policy offline using batch reinforcement learning. This approach makes it possible to train agents to perform challenging manipulation tasks like stacking rigid objects.

New Benchmark for Stacking

DeepMind recently introduced RGB-Stacking as the new benchmark for vision-based robotic manipulation tasks. Here the robot has to learn how to grasp different objects and balance them over each other. It was different from previous works because of the diversity of the objects used and the variety of empirical evaluations performed to verify the accuracy of the results. 

Credit: DeepMind

The results demonstrated that complex multi-object manipulation can be learnt using a combination of simulation and real-world data. The experiment could also suggest a strong baseline for generalisation to novel objects. 

This experiment is considered a major advancement in DeepMind’s endeavour towards making generalisable and useful robots. The authors will now work to make robots better understand the interaction with objects of different geometries. The RGB-Stacking benchmark has been open-sourced along with the designs for building real-robot RGB-stacking environments, RGB-object models and information for 3D printing. 


MuJoCo is a physics engine simulator that facilitates research and development in fields that require fast and accurate simulations like robotics, biomechanics, graphics, animation, etc. Developed by Emo Todorov for Roboti, MuJoCo is one of the first full-featured simulators designed from scratch for model-based optimisation through contacts. Before DeepMind’s acquisition, MuJoCo was a commercial product between 2015 and 2021.

MuJoCo helps in scaling up computationally intensive techniques like optimal control, system identification, physically consistent state estimation, and automated mechanism design before applying them to complex dynamic systems in contact-rich behaviours. It also has applications like testing and validating control schemes before deploying on physical robots, gaming, and interactive scientific visualisation.

Wrapping up

This is probably a slow phase for research and development work in robotics. DeepMind rival OpenAI, after investing many years of research, resources and efforts into robotics, finally decided to disband its robotics research team and shift focus to domains where data is more readily available. On the industry side, too, several robotics-based companies have shut shop or are undergoing major losses. Given the circumstances, robotics, despite being such a lucrative industry, has limited to no buyers.

Backed by Alphabet, DeepMind’s progress has helped it hold the flag high in this field over the past few years.

More Great AIM Stories

Shraddha Goled
I am a technology journalist with AIM. I write stories focused on the AI landscape in India and around the world with a special interest in analysing its long term impact on individuals and societies. Reach out to me at

Our Upcoming Events

Conference, Virtual
Genpact Analytics Career Day
3rd Sep

Conference, in-person (Bangalore)
Cypher 2022
21-23rd Sep

Conference, in-person (Bangalore)
Machine Learning Developers Summit (MLDS) 2023
19-20th Jan, 2023

Conference, in-person (Bangalore)
Data Engineering Summit (DES) 2023
21st Apr, 2023

Conference, in-person (Bangalore)
MachineCon 2023
23rd Jun, 2023

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM

Council Post: How to Evolve with Changing Workforce

The demand for digital roles is growing rapidly, and scouting for talent is becoming more and more difficult. If organisations do not change their ways to adapt and alter their strategy, it could have a significant business impact.

All Tech Giants: On your Mark, Get Set – Slow!

In September 2021, the FTC published a report on M&As of five top companies in the US that have escaped the antitrust laws. These were Alphabet/Google, Amazon, Apple, Facebook, and Microsoft.

The Digital Transformation Journey of Vedanta

In the current digital ecosystem, the evolving technologies can be seen both as an opportunity to gain new insights as well as a disruption by others, says Vineet Jaiswal, chief digital and technology officer at Vedanta Resources Limited

BlenderBot — Public, Yet Not Too Public

As a footnote, Meta cites access will be granted to academic researchers and people affiliated to government organisations, civil society groups, academia and global industry research labs.