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:
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:
- 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
- Application of these techniques in robotic system testbeds, demonstrating this capability within an integrated system with live data.
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 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.
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:
- 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.
- 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!
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.
Our paper proposes a new way to account for “passivity” structure in Dynamic Bayesian Networks, which enables more efficient belief computations and through that improvements for systems modelled by POMDPs and so on. It was surprising to me when we started this project that despite significant earlier attention to exploiting conditional independence structure, there had not been work on these notions of using constraints (often imposed by physics of other background regularities) in making belief updates more efficient.
Please read the paper in JAIR: http://dx.doi.org/10.1613/jair.5044, abstract reproduced below:
Stefano V. Albrecht and Subramanian Ramamoorthy (2016) “Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks”, Volume 55, pages 1135-1178.
Dynamic Bayesian networks (DBNs) are a general model for stochastic processes with partially observed states. Belief filtering in DBNs is the task of inferring the belief state (i.e. the probability distribution over process states) based on incomplete and noisy observations. This can be a hard problem in complex processes with large state spaces. In this article, we explore the idea of accelerating the filtering task by automatically exploiting causality in the process. We consider a specific type of causal relation, called passivity, which pertains to how state variables cause changes in other variables. We present the Passivity-based Selective Belief Filtering (PSBF) method, which maintains a factored belief representation and exploits passivity to perform selective updates over the belief factors. PSBF produces exact belief states under certain assumptions and approximate belief states otherwise, where the approximation error is bounded by the degree of uncertainty in the process. We show empirically, in synthetic processes with varying sizes and degrees of passivity, that PSBF is faster than several alternative methods while achieving competitive accuracy. Furthermore, we demonstrate how passivity occurs naturally in a complex system such as a multi-robot warehouse, and how PSBF can exploit this to accelerate the filtering task.
I will be giving two talks, to a broad audience, on Thursday, 19th November.
The first of these is in a interdisciplinary workshop on Embodied Mind, Embodied Design, aimed at connecting researchers within the university with a shared interest in this general direction. The partial lineup of speakers looks interesting, ranging from psychology and health science to music. Those in Edinburgh University might look into this event happening in Room G32, 7 George Square.
The second is to the Edinburgh U3A Science group. I will be speaking to this group about Interactively Intelligent Robots: Prospects and Challenges.