Encoding practical knowledge about everyday activities has proven difficult, and is a limiting factor in the progress of autonomous robotics. Learning approaches, e.g. imitation learning from human data, have been used as a way to circumvent this difficulty. While such approaches are on the right track, they require comprehensive knowledge modelling about the data present in records of activity episodes, and about the skills one attempts to have the robot learn. We provide a list of competency questions such knowledge modelling should answer, summarize some recent developments in this direction, and finish with a few open problems.
Despite research interest into autonomous robot systems, progress in this field is slow. It takes considerable effort to teach a robot tasks which appear simple to a human, e.g. cracking an egg, and therefore autonomous robotic helpers for households or care facilities remain only a distant possibility. It is difficult to make explicit the practical knowledge of how to perform everyday tasks – it may be easy to walk, but is definitely hard to program a robot to do it. Recent development efforts attempt to elicit such knowledge indirectly: collect data from humans performing an activity, and use it to learn a model for inferring parameters or heuristics for organizing an activity’s structure. Alternatively, learning may use data collected from other robots’ attempts to perform the task.
We think such approaches are broadly correct, but we insist on the necessity to
develop introspectable, formalized knowledge representations to guide them. The problem
with machine learning, as a growing body of research demonstrates, is its tendency to
learn shortcuts from idiosyncracies of the training data rather than the function intended
by the human developer [
Some of the authors of this paper are actively working on the development of an infrastructure to gather, store, and query information about activity episodes2. An episode is recorded in our infrastructure as a Narratively-Enabled Episodic Memory (NEEM). We highlight the “narrative” part: a rich level of semantics on top of the records of raw signals is necessary if such records are to be useful as training data, and we outline in this paper that the semantics should clarify what problems and tasks the data are about.
We begin with a list of competency questions that, ideally, knowledge modelling for autonomous robots should be able to answer. In particular, being able to answer such questions helps to acquire knowledge via learning and to transfer it between agents.
be executed in different ways but not all are equally acceptable by humans: wasting of resources, very fast/slow movements, breaking of proxemic rules, causing danger are all behavioral factors that an ideal robot should take into account.
Appropriateness is often cultural and contextual. 2. What kind of knowledge is necessary to achieve a task? Planning how to execute a task generally requires different types of knowledge: possible and allowed actions, likely consequences, factual and typical location of items, procedural “flair” (e.g. controller parametrizations), expectations about other agents, etc. 3. What does a particular system believe to be true? This kind of questions are important to explain why a system makes certain decisions, why it implements them in a certain way, and why the resulting behavior is justified or not. 4. What knowledge can be transferred between agents? It is important to understand what items of knowledge may be transferable, the level of abstraction at which they are most useful, and how to adapt them to the capabilities of the robot. Declarative knowledge can often be copied as-is, but practical knowledge is usually agent-dependent. Yet, it is expected that there is a level of commonality among different agents that have the “same skills”.
what data is relevant and what events are considered (un)likely. Given the sensitivity of machine learning models to biases in their training data, it is not just the availability of the data that is important; we need data about the data.
There is a very vast literature about applying machine learning techniques to a variety of applications, including robotics. We will only summarize a few results in this section, with a focus on how they relate to the competency questions we have identified. We believe the research results we discuss are typical of the larger situation in the field.
Ethics and AI is itself a hot topic for philosophical and vision papers, but we are not aware of any results tackling this with machine learning. To our knowledge, there are no 2Querying the activity episodes we have stored is possible at open-ease.org datasets or benchmarks for what would be moral or culturally appropriate behavior – i.e., the usual way of pumping out results from machine learning is not applicable –, and this is clearly a situation that needs principled modelling of what norms on behavior are, how they can be acquired from humans, and how they might be verified in a learned system.
In an attempt to provide more generalizable action concepts, carefully engineered
curricula were used to help an agent learn how to act in a simulated pixelworld [
A recent report surveys opportunities for knowledge graph techniques for explainable
AI [
The correspondence problem – e.g. different body shapes – is well known in imitation
learning and approaches to adjust trajectories from a human teacher to a robot student
exist [
Unfortunately many papers tend to not put much weight on this issue and its
implications for what a robot learns. E.g. a claim is made that, via imitation learning, a robot is
taught to kick a stationary ball forward [
Knowledge representation and reasoning in autonomous robot control is a fairly
extensive field of research with developments in both service and industrial robotics.
OlivaresAlarcos et al. provide a comprehensive comparison of different approaches [
An immediate problem is that knowledge is often implicitly encoded, e.g. in the
control system of the robot or in physical models for simulation, raising the question of how
to organize such heterogeneous information sources in a coherent knowledge base [
The need for a distributed knowledge service where experiential data for robots
could be pooled and queried on demand has become clear in recent years. Fundamental
work has been done in the RoboEarth project [
In order for a repository of episodic memories to be useful as a generator of training
data or even a “cheat sheet” to suggest ready-made plans and parametrizations to the
robot, it should be able to answer several questions such as, is there any episode from
a situation similar to the one a robot wants to learn about? If so, how many episodes
are matched? Can the performance in the recorded episode be adapted to the current
situation? Some of these questions are addressed in the works presented in [
To judge similarity of episodes, information present in a recorded episode should
also allow answering questions such as what are the entities in the environment, what are
their initial states, what are the sensors the robot/environment has, what type of sensors
can be used to perceive the environment in the current situation [
As we have previously mentioned in our discussion of learning approaches for
robots, it should be possible to store episodes of failure as well, both to understand what
kind of failures can happen, when they do, and how to recover from them. This requires
an ontological characterization of failure, its causal mechanisms, its impact on other
activities the robot might perform, and what the criteria for successful failure handling are.
These questions are addressed in the work presented in [
Stored episodes must also contain information relevant for the task and motion
planning (TAMP) modules of a robot, such as: 1) the appropriate interaction parameters
(friction, slip, maximum force) required by physics-based motion planners to correctly
interact with rigid bodies; 2) the spatial relations (on, inside, right, etc.) between the
objects in a cluttered scenario; 3) the feasibility of actions due to geometric issues like arm
reachability or collisions; 4) the feasibility of actions due to object features (e.g.,
overweight objects); 5) the geometric constrains that limit the motion planner space; 6) action
constraints regarding the interaction with objects; and 7) the initial scene for the planner
regarding for instance the potential grasp poses. Knowledge can play a significant role to
guide the TAMP by answering all aforementioned points [
In this paper we have discussed knowledge transfer as a means to acquire and adapt suitable behaviors to execute tasks, and summarized some existing work into achieving this with knowledge-enabled approaches. If we look at this issue in full generality, the discussion in Sec. 3 leaves out important aspects which are hard to model, and that we anticipated in part in the list of competency questions of Sec. 1. In complex socio-technical systems, e.g. hospitals or retirement homes, it is not enough to learn how to accomplish a task in a standard way. When to act, how to adapt to surrounding events, how to interact with nearby humans are important aspects to the success of an activity, but these aspects are culturally dependent and rely on a shared understanding of the situation.
Some formal proposals have pushed forward in terms of a trait-based theory of
culture [
Another issue illustrated by our competency questions is modelling capabilities.
Intuitively speaking, a capability is something which, if an agent possesses it, allows that
agent to perform some kind of tasks. Complexity comes from finding a principled,
formal answer about what kind of entity a capability is, what other entities it might depend
on and in what way, and how it might compare to analogous capabilities of different
agents. A simple capability model might be obtained by mapping sets of the robot’s
hardware parts to tasks; an example of this in the multi-robot, outdoor setting can be seen
in the SHERPA project [
This work was partially funded by Deutsche Forschungsgemeinschaft (DFG) through the Collaborative Research Center 1320, EASE and by the Spanish Government through the project DPI2016-80077-R. M. Diab is supported by the Spanish Government through the grants FPI 2017.