Generating predicate suggestions based on the space of plans: an example of planning with preferences.

Task planning in human-robot environments tends to be particularly complex as it involves additional uncertainty introduced by the human user. Several plans, entailing few or various differences, can be obtained to solve the same given task. To choose among them, the usual least-cost plan criteria is not necessarily the best option, because here, human constraints and preferences come into play. Knowing these user preferences is very valuable to select an appropriate plan, but the preference values are usually hard to obtain. In this context, we propose the Space-of-Plans-based Suggestions (SoPS) algorithms that can provide suggestions for some planning predicates, which are used to define the state of the environment in a task planning problem where actions modify the predicates. We denote these predicates as suggestible predicates, of which user preferences are a particular case. The first algorithm is able to analyze the potential effect of the unknown predicates and provide suggestions to values for these unknown predicates that may produce better plans. The second algorithm is able to suggest changes to already known values that potentially improve the obtained reward. The proposed approach utilizes a Space of Plans Tree structure to represent a subset of the space of plans. The tree is traversed to find the predicates and the values that would most increase the reward, and output them as a suggestion to the user. Our evaluation in three preference-based assistive robotics domains shows how the proposed algorithms can improve task performance by suggesting the most effective predicate values first.

Introducing CARESSER: A framework for in situ learning robot social assistance from expert knowledge and demonstrations.

Socially assistive robots have the potential to augment and enhance therapist's effectiveness in repetitive tasks such as cognitive therapies. However, their contribution has generally been limited as domain experts have not been fully involved in the entire pipeline of the design process as well as in the automatisation of the robots' behaviour. In this article, we present aCtive leARning agEnt aSsiStive bEhaviouR (CARESSER), a novel framework that actively learns robotic assistive behaviour by leveraging the therapist's expertise (knowledge-driven approach) and their demonstrations (data-driven approach). By exploiting that hybrid approach, the presented method enables in situ fast learning, in a fully autonomous fashion, of personalised patient-specific policies. With the purpose of evaluating our framework, we conducted two user studies in a daily care centre in which older adults affected by mild dementia and mild cognitive impairment (N = 22) were requested to solve cognitive exercises with the support of a therapist and later on of a robot endowed with CARESSER. Results showed that: (i) the robot managed to keep the patients' performance stable during the sessions even more so than the therapist; (ii) the assistance offered by the robot during the sessions eventually matched the therapist's preferences. We conclude that CARESSER, with its stakeholder-centric design, can pave the way to new AI approaches that learn by leveraging human-human interactions along with human expertise, which has the benefits of speeding up the learning process, eliminating the need for the design of complex reward functions, and finally avoiding undesired states.

Evaluation of an exercise-enabling control interface for powered wheelchair users: a feasibility study with Duchenne muscular dystrophy.

BACKGROUND: Powered wheelchairs are an essential technology to support mobility, yet their use is associated with a high level of sedentarism that can have negative health effects for their users. People with Duchenne muscular dystrophy (DMD) start using a powered wheelchair in their early teens due to the loss of strength in their legs and arms. There is evidence that low-intensity exercise can help preserve the functional abilities of people with DMD, but options for exercise when sitting in a powered wheelchair are limited. METHODS: In this paper, we present the design and the feasibility study of a new version of the MOVit device that allows powered-wheelchair users to exercise while driving the chair. Instead of using a joystick to drive the wheelchair, users move their arms through a cyclical motion using two powered, mobile arm supports that provide controller inputs to the chair. The feasibility study was carried out with a group of five individuals with DMD and five unimpaired individuals. Participants performed a series of driving tasks in a wheelchair simulator and on a real driving course with a standard joystick and with the MOVit 2.0 device. RESULTS: We found that driving speed and accuracy were significantly lowered for both groups when driving with MOVit compared to the joystick, but the decreases were small (speed was 0.26 m/s less and maximum path error was 0.1 m greater). Driving with MOVit produced a significant increase in heart rate (7.5 bpm) compared to the joystick condition. Individuals with DMD reported a high level of satisfaction with their performance and comfort in using MOVit. CONCLUSIONS: These results show for the first time that individuals with DMD can easily transition to driving a powered wheelchair using cyclical arm motions, achieving a reasonable driving performance with a short period of training. Driving in this way elicits cardiopulmonary exercise at an intensity found previously to produce health-related benefits in DMD.

Growth Signatures of Rosette Plants from Time-Lapse Video.

Plant growth is a dynamic process, and the precise course of events during early plant development is of major interest for plant research. In this work, we investigate the growth of rosette plants by processing time-lapse videos of growing plants, where we use Nicotiana tabacum (tobacco) as a model plant. In each frame of the video sequences, potential leaves are detected using a leaf-shape model. These detections are prone to errors due to the complex shape of plants and their changing appearance in the image, depending on leaf movement, leaf growth, and illumination conditions. To cope with this problem, we employ a novel graph-based tracking algorithm which can bridge gaps in the sequence by linking leaf detections across a range of neighboring frames. We use the overlap of fitted leaf models as a pairwise similarity measure, and forbid graph edges that would link leaf detections within a single frame. We tested the method on a set of tobacco-plant growth sequences, and could track the first leaves of the plant, including partially or temporarily occluded ones, along complete sequences, demonstrating the applicability of the method to automatic plant growth analysis. All seedlings displayed approximately the same growth behavior, and a characteristic growth signature was found.

Consistent depth video segmentation using adaptive surface models.

We propose a new approach for the segmentation of 3-D point clouds into geometric surfaces using adaptive surface models. Starting from an initial configuration, the algorithm converges to a stable segmentation through a new iterative split-and-merge procedure, which includes an adaptive mechanism for the creation and removal of segments. This allows the segmentation to adjust to changing input data along the movie, leading to stable, temporally coherent, and traceable segments. We tested the method on a large variety of data acquired with different range imaging devices, including a structured-light sensor and a time-of-flight camera, and successfully segmented the videos into surface segments. We further demonstrated the feasibility of the approach using quantitative evaluations based on ground-truth data.

Local stimulus disambiguation with global motion filters predicts adaptive surround modulation.

Humans have no problem segmenting different motion stimuli despite the ambiguity of local motion signals. Adaptive surround modulation, i.e., the apparent switching between integrative and antagonistic modes, is assumed to play a crucial role in this process. However, so far motion processing models based on local integration have not been able to provide a unifying explanation for this phenomenon. This motivated us to investigate the problem of local stimulus disambiguation in an alternative and fundamentally distinct motion-processing model which uses global motion filters for velocity computation. Local information is reconstructed at the end of the processing stream through the constructive interference of global signals, i.e., inverse transformations. We show that in this model local stimulus disambiguation can be achieved by means of a novel filter embedded in this architecture. This gives rise to both integrative and antagonistic effects which are in agreement with those observed in psychophysical experiments with humans, providing a functional explanation for effects of motion repulsion.

General robot kinematics decomposition without intermediate markers.

The calibration of serial manipulators with high numbers of degrees of freedom by means of machine learning is a complex and time-consuming task. With the help of a simple strategy, this complexity can be drastically reduced and the speed of the learning procedure can be increased. When the robot is virtually divided into shorter kinematic chains, these subchains can be learned separately and hence much more efficiently than the complete kinematics. Such decompositions, however, require either the possibility to capture the poses of all end effectors of all subchains at the same time, or they are limited to robots that fulfill special constraints. In this paper, an alternative decomposition is presented that does not suffer from these limitations. An offline training algorithm is provided in which the composite subchains are learned sequentially with dedicated movements. A second training scheme is provided to train composite chains simultaneously and online. Both schemes can be used together with many machine learning algorithms. In the simulations, an algorithm using parameterized self-organizing maps modified for online learning and Gaussian mixture models (GMMs) were chosen to show the correctness of the approach. The experimental results show that, using a twofold decomposition, the number of samples required to reach a given precision is reduced to twice the square root of the original number.

Learning inverse kinematics: reduced sampling through decomposition into virtual robots.

We propose a technique to speedup the learning of the inverse kinematics of a robot manipulator by decomposing it into two or more virtual robot arms. Unlike previous decomposition approaches, this one does not place any requirement on the robot architecture, and thus, it is completely general. Parametrized self-organizing maps are particularly adequate for this type of learning, and permit comparing results directly obtained and through the decomposition. Experimentation shows that time reductions of up to two orders of magnitude are easily attained.

Speeding up the learning of robot kinematics through function decomposition.

The main drawback of using neural networks or other example-based learning procedures to approximate the inverse kinematics (IK) of robot arms is the high number of training samples (i.e., robot movements) required to attain an acceptable precision. We propose here a trick, valid for most industrial robots, that greatly reduces the number of movements needed to learn or relearn the IK to a given accuracy. This trick consists in expressing the IK as a composition of learnable functions, each having half the dimensionality of the original mapping. Off-line and on-line training schemes to learn these component functions are also proposed. Experimental results obtained by using nearest neighbors and parameterized self-organizing map, with and without the decomposition, show that the time savings granted by the proposed scheme grow polynomially with the precision required.

Comparison of simulated annealing and mean field annealing as applied to the generation of block designs.

This paper describes an experimental comparison between a discrete stochastic optimization procedure (Simulated Annealing, SA) and a continuous deterministic one (Mean Field Annealing), as applied to the generation of Balanced Incomplete Block Designs (BIBDs). A neural cost function for BIBD generation is proposed with connections of arity four, and its continuous counterpart is derived, as required by the mean field formulation. Both strategies are optimized with regard to the critical temperature, and the expected cost to the first solution is used as a performance measure for the comparison. The results show that SA performs slightly better, but the most important observation is that the pattern of difficulty across the 25 problem instances tried is very similar for both strategies, implying that the main factor to success is the energy landscape, rather than the exploration procedure used.