Discussion at the Disruptive Innovation Festival

I recently participated in this event, organised by the Ellen MacArthur Foundation, on the provocatively titled topic of “Maybe the Robot Invasion is a Good Thing”. In fact, the event was more a discussion on all things AI and robotics, with host Jules Hayward, with an emphasis in the second half on the social impact of these technologies. The Festival organisers have recorded the session and made it available (I am told until shortly after Christmas). If you were interested in listening, here is the link:



Postdoctoral Research Positions within Offshore Energy Hub

Following the earlier announcement regarding the DARPA XAI project, we have further positions open within my group: https://www.vacancies.ed.ac.uk/pls/corehrrecruit/erq_jobspec_version_4.jobspec?p_id=041917.

“Project F” pertains to Intelligent HRI with Explainable AI, including work on:

  1. Techniques to enable understanding causal structure of specific decisions, towards diagnosis and model/policy repair
    • Causal interpretation of opaque (machine learnt) models, reasoning about “why”, “but for”, etc.
    • Tools for (statistical) model criticism and repair
  2. Application of these techniques in robotic system testbeds, demonstrating this capability within an integrated system with live data.

Postdoctoral position in Reinforcement Learning and Explainable AI

Applications are invited for the position of Postdoctoral Research Associate in a project funded by DARPA within the Explainable Artificial Intelligence programme. The position will be based in the School of Informatics at the University of Edinburgh.

The project, titled COGLE: Common Ground Learning and Explanation, is in collaboration with Palo Alto Research Centre Inc. (PARC), Carnegie Mellon University, University of Michigan, Florida Institute for Human & Machine Cognition and the US Military Academy at West Point. The project aim is to develop a highly interactive sense-making system which is able to explain the learned performance capabilities of autonomous systems to human users. Towards this end, our group will focus on machine learning methods to construct decision policies for an autonomous system to perform a variety of missions, as well as methods to induce representations of the models and policies at varying levels of abstraction.

The particular focus of the Postdoctoral Research Associate on this project will be to develop (hierarchical) methods for task and motion planning, to develop methods for program induction and to connect the two in order to devise novel methods for reinforcement learning of policies that are also amenable to explanation and causal reasoning. Experiments will be carried out in domains including flight mission planning with Unmanned Aerial Vehicles (UAVs). The work in this project is synergistic to other similarly funded projects within our research group. So, if the Research Associate were so inclined, there is the opportunity to collaborate with other researchers who are applying similar methods to a variety of other robotics problems, ranging from laboratory scale mobile manipulation robots such as the PR2 to underwater, ground and aerial robots operating in hazardous environments such as offshore energy installations.

The post is available from 1 December 2017 for 3 years. The closing date for applications is 27 November 2017.
Further details and a link to the online application portal are available at

Interview with RAD student, Daniel Angelov

One of our students, Daniel Angelov, has spent the past few months at Xerox PARC as an intern. He has been doing interesting things associated with the COGLE project I mentioned earlier, part of the DARPA XAI programme.

The folks at PARC have put up this interview on their blog, in which Daniel talks about his work and time there:


Project COGLE, within the DARPA XAI Programme

We have been awarded one of the projects under the DARPA Explainable AI programme, to be kicked off next week. Our project, entitled COGLE (Common Ground Learning and Explanation), will be coordinated by Xerox Palo Alto Research Centre, and I will a PI leading technical efforts on the machine learning side of the architecture.

COGLE will be a highly interactive sense-making system for explaining the learned performance capabilities of an autonomous system and the history that produced that learning. COGLE will be initially developed using an autonomous Unmanned Aircraft System (UAS) test bed that uses reinforcement learning (RL) to improve its performance. COGLE will support user sensemaking of autonomous system decisions, enable users to understand autonomous system strengths and weaknesses, convey an understanding of how the system will behave in the future, and provide ways for the user to improve the UAS’s performance.

To do this, COGLE will:

  1. Provide specific interactions in sensemaking user interfaces that directly support modes of human explanation known to be effective and efficient in human learning and understanding.
  2. Support mapping (grounding) of human conceptualizations onto the RL representations and processes.

This area is becoming one that is increasingly being discussed in the public sphere, in the context of the increasing adoption of AI into daily lives, e.g., see this article in the MIT Technology Review and this one in Nautilus, both referring directly to this DARPA programme. I look forward to contributing to this theme!

The program induction route to explainability and safety in autonomous systems

I will be giving a talk, as part of the IPAB seminar series, through which I will try to further develop this framing of the problem which I expect our group to try to solve in the medium term. In a certain sense, my case will hark back to fairly well established techniques familiar to engineers but slowly lost with the coming of statistical methods into the robotics space. Also, many others are picking up on the underlying needs, e.g., this recent article in the MIT Technology Review gives a popular account of current sentiment among some in the AI community.


The program induction route to explainability and safety in autonomous systems


The confluence of advances in diverse areas including machine learning, large scale computing and reliable commoditised hardware have brought autonomous robots to the point where they are poised to be genuinely a part of our daily lives. Some of the application areas where this seems most imminent, e.g., autonomous vehicles, also bring with them stringent requirements regarding safety, explainability and trustworthiness. These needs seem to be at odds with the ways in which recent successes have been achieved, e.g., with end-to-end learning. In this talk, I will try to make a case for an approach to bridging this gap, through the use of programmatic representations that intermediate between opaque but efficient learning methods and other techniques for reasoning that benefit from ’symbolic’ representations.

I will begin by framing the overall problem, drawing on some of the motivations of the DARPA Explainable AI programme (under the auspices of which we will be starting a new project shortly) and on extant ideas regarding safety and dynamical properties in the control theorists’ toolbox – also noting where new techniques have given rise to new demands.

Then, I will shift focus to results from one specific project, for Grounding and Learning Instances through Demonstration and Eye tracking (GLIDE), which serves as an illustration of the starting point from which we will proceed within the DARPA project. The problem here is to learn the mapping between abstract plan symbols and their physical instances in the environment, i.e., physical symbol grounding, starting from cross-modal input provides the combination of high- level task descriptions (e.g., from a natural language instruction) and a detailed video or joint angles signal. This problem is formulated in terms of a probabilistic generative model and addressed using an algorithm for computationally feasible inference to associate traces of task demonstration to a sequence of fixations which we call fixation programs.

I will conclude with some remarks regarding ongoing work that explicitly addresses the task of learning structured programs, and using them for reasoning about risk analysis, exploration and other forms of introspection.

Team Edina selected to Compete for Alexa Prize

My student, Emmanuel Kahembwe, is part of Team Edina – consisting of students and postdoctoral researchers from the School of Informatics at the University of Edinburgh – who are one of 12 teams competing for The Alexa Prize. The grand challenge is to build a socialbot that can converse coherently and engagingly with humans on popular topics for 20 minutes.

Let us wish them all the best and I am very curious to see what comes out of this competition!