Primitive Skills Research Articles

Concurrent Skill Composition Using Ensemble of Primitive Skills

Concurrent Skill Composition Using Ensemble of Primitive Skills

Automatic high-level motion sequencing methods for enabling multi-tasking construction robots

Robots are expected to play an important role in future construction work. However, they are not yet widely adopted by the industry because it is difficult and expensive to program robots to conduct a variety of construction tasks. This paper presents a method for intuitively and flexibly teaching robots to perform various construction tasks through demonstrations. Robots are first programmed with basic skill primitives and then learn the sequencing of these primitive skills to perform different types of construction work under the guidance of human supervisors. The construction workflow and the interaction processes are enabled by a process-level digital twin system. Case studies with three assembly scenarios and a wooden frame construction experiment are used to present and verify the proposed method. The proposed approach enables automatic robot motion sequencing abilities through Learning from Demonstration and has the potential to enable the widespread adoption of robots on construction sites.

‘I know how to say it, but I still don’t know it in my hands’: examining practices and epistemology in Forest Education

In recent years, Forest Education has gained increasing traction around the world. Yet its unique features, as well as their relations with other outdoor environmental education approaches, remain undertheorized. This study explores the pedagogical practices of one emerging strand of Forest Education, and the epistemology underpinning it, in order to better position it with respect to other environmental education approaches. The study is based on ethnographic fieldwork that included participatory observations and interviews in a leading Israeli Forest Education organization. We identified four key pedagogical practices: outdoor play, primitive skills and crafts, sensing, and dwelling. These, we argue, reflect an epistemology in which knowledge and learning are situated in the immediate embodied context and sensory experiences, and are intended to facilitate a meaningful connection with nature. This epistemology prioritizes such modes of learning over abstraction, generalization and transfer, which are often central to science-oriented environmental education approaches.

Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity

In real-world environments, robots need to be resilient to damages and robust to unforeseen scenarios. Quality-Diversity (QD) algorithms have been successfully used to make robots adapt to damages in seconds by leveraging a diverse set of learned skills. A high diversity of skills increases the chances of a robot to succeed at overcoming new situations since there are more potential alternatives to solve a new task. However, finding and storing a large behavioural diversity of multiple skills often leads to an increase in computational complexity. Furthermore, robot planning in a large skill space is an additional challenge that arises with an increased number of skills. Hierarchical structures can help to reduce this search and storage complexity by breaking down skills into primitive skills. In this article, we extend the analysis of the Hierarchical Trial and Error algorithm, which uses a hierarchical behavioural repertoire to learn diverse skills and leverages them to make the robot adapt quickly in the physical world. We show that the hierarchical decomposition of skills enables the robot to learn more complex behaviours while keeping the learning of the repertoire tractable. Experiments with a hexapod robot both in simulation and the physical world show that our method solves a maze navigation task with up to, respectively, 20% and 43% less actions than the best baselines while having 78% less complete failures.

Geometric Task Networks: Learning Efficient and Explainable Skill Coordination for Object Manipulation

Complex manipulation tasks can contain various execution branches of primitive skills in sequence or in parallel under different scenarios. Manual specifications of such branching conditions and associated skill parameters are not only error-prone due to corner cases, but also quickly untraceable given a large number of objects and skills. On the other hand, learning from demonstration has increasingly shown to be an intuitive and effective way to program such skills for industrial robots. Parameterized skill representations allow generalization over new scenarios, which however makes the planning process much slower thus unsuitable for online applications. In this article, we propose a hierarchical and compositional planning framework that learns a geometric task network (GTN) from exhaustive planners, without any manual inputs. A GTN is a goal-dependent task graph that encapsulates both the transition relations among skill representations and the geometric constraints underlying these transitions. This framework has shown to improve dramatically the offline learning efficiency, the online performance, and the transparency of decision process, by leveraging the task-parameterized models. We demonstrate the approach on a 7-DoF robot arm both in simulation and on hardware solving various manipulation tasks.

Hafting with a Living Tree: A Historical Review of the Alleged Practice of Growth-Assisted Hafting

ABSTRACT Despite facing the challenges of preservation and rarity of evidence in the archaeological record, hafting methods are a research pursuit of archaeologists seeking to explain the construction of weapons and tools. Various works have included references to a unique method of hafting, referred to in this article as growth-assisted hafting, which involved inserting a stone into a living tree branch and waiting for wood growth to encase the inclusion before harvesting and constructing the knife, club or axe. Such a method would lack toolmarks and exhibit some evidence in wood grain patterns and possible abnormal fiber build-up of continued tree growth around the inclusion. This paper is a historical review of the alleged practice based on accounts from around the world and how the practice has re-appeared in the modern primitive skills subculture.

A Modular Dynamic Sensorimotor Model for Affordances Learning, Sequences Planning, and Tool-Use

This paper proposes a computational model for learning robot control and sequence planning based on the ideomotor principle. This model encodes covariation laws between sensors and motors in a modular fashion and exploits these primitive skills to build complex action sequences, potentially involving tool-use. Implemented for a robotic arm, the model starts with raw unlabeled sensor and motor vectors and autonomously assigns functions to neutral objects in the environment. Our experimental evaluation highlights the emergent properties of such a modular system and we discuss their consequences from ideomotor and sensorimotor-theoretic perspectives.

Sustainable Livelihood For Scheduled Tribes: Perspectives On Minor Forest Produce In India

The tribal population in India is at different levels of socio-economic development. There are tribes which live in the forests and are exclusively dependent on forests for their livelihood by practicing hunting and food gathering. With their primitive technology, limited skills and traditional and ritual practices, their entire lifestyle revolves around the forests. On the other hand, there are a few tribal communities in the eastern part of the country, which have been totally assimilated in national mainstream. This paper intends to explore issues concerning Minor forest produce in Indian tribal areas along with role of civic bodies in this regard.

Event review: 1st Annual Outdoors Without Limits (OWL) knap-in

In June of 2014, Outdoors Without Limits (OWL), a national non-profit organization that promotes awareness and teamwork between disabled and non-disabled individuals, sponsored their first knap-in and primitive skills gathering.

A psychology based approach for longitudinal development in cognitive robotics

A major challenge in robotics is the ability to learn, from novel experiences, new behavior that is useful for achieving new goals and skills. Autonomous systems must be able to learn solely through the environment, thus ruling out a priori task knowledge, tuning, extensive training, or other forms of pre-programming. Learning must also be cumulative and incremental, as complex skills are built on top of primitive skills. Additionally, it must be driven by intrinsic motivation because formative experience is gained through autonomous activity, even in the absence of extrinsic goals or tasks. This paper presents an approach to these issues through robotic implementations inspired by the learning behavior of human infants. We describe an approach to developmental learning and present results from a demonstration of longitudinal development on an iCub humanoid robot. The results cover the rapid emergence of staged behavior, the role of constraints in development, the effect of bootstrapping between stages, and the use of a schema memory of experiential fragments in learning new skills. The context is a longitudinal experiment in which the robot advanced from uncontrolled motor babbling to skilled hand/eye integrated reaching and basic manipulation of objects. This approach offers promise for further fast and effective sensory-motor learning techniques for robotic learning.

Medium-Range Forecast Sensitivity to the Background State and Background Error Statistics in a Global Data Assimilation and Prediction System

The increase in the medium-range forecast skill of global models is attributable to the improvement of the initial condition, model dynamics, and physics. In this study, we evaluated the role of the background state and background error statistics (BES) on a medium-range forecast testbed, using the Global/Regional Integrated Model system (GRIMs) that incorporates the National Center for Environmental Prediction (NCEP) Gridpoint Statistics Interpolation (GSI). In addition to the control run, in which the initial condition is obtained from the NCEP Global Data Assimilation System (GDAS) analysis, four additional experiments with different background states and BES are executed to evaluate the impacts of the background state and the BES on forecast skills. The standard background fields are produced from the sophisticated, higher resolution NCEP Global Data Assimilation System (GDAS), whereas the other background fields are produced from the GRIMs through cycle runs every 6 hours. Further, the two kinds of BES are calculated from the NCEP Global Forecast System (GFS) and the GRIMs, respectively. Evaluations are performed in August 2010, with the focus on the 500-hPa geopotential height and precipitation. The experiment simulated with results from high-quality background fields performs better than when using results of low-quality background fields with respect to the 500-hPa geopotential height Anomaly Correlation (AC). This is true for both North and South Hemisphere results. The impact of BES dose not responds much towards primitive forecast skills, but it influences the forecast skill after day 7. In contrast to the large-scale features, the forecast skills of precipitation show the overall improvement of land precipitation with the support of the cycle run.

Report on Knapping Activities in America

THE LAST TIME I demonstrated flintknapping and talked about the archaeology of stone tools to a grade school class, the teachers informed me that in their survey of “what I want to be when I grow up” the next week, a majority of students had decided to become archaeologists. God forbid! But at least they all know now that archaeologists study people, not dinosaurs. Anyone who can make “arrowheads” and other simple tools, play with the kind of sharp objects usually forbidden by parents and banned from schools, and talk amusingly about the different lives of prehistoric people is, for a brief space, a hero. OK, fifth graders are an easy audience for that sort of thing, but to some extent, so are their elders. Archaeologists who complain about the disinterested or even hostile public are not taking advantage of some easy connections among the large numbers of people attracted to “primitive skills.” Flintknappers are only one of several more or less organized subcultures where an interested audience, and even friends and colleagues, can be found among the non-academic public. Moreover, it’s a two-way street: many knappers would like more archaeological knowledge, and many archaeologists could learn a lot about stone tools from exploring the knap-in world. Since this journal is mostly read by (too few) academics working with stone tools, one of my major goals in writing this article is to point out to my colleagues that the non-academic knapping world provides many resources that academics should be aware of, as well as a few less pleasing aspects.

幾何学的シンボル操作による多様な動作パターンの認識・生成を実現する原始シンボル空間の構成法

Humans’ primitive skill of imitative learning is regarded as an origin of human intelligence because it is said that imitation is fundamental function for communication and symbol manipulation. M.Donald has proposed “mimesis model” in order to approach to a symbol emergence framework from behavior recognition/generation for humanoid robots. In this paper, we propose a mathematical model for motion recognition and generation as combination of basic motions by proto-symbol manipulation which is abstract expression of motion patterns. In order to describe the proto-symbol manipulation as geometric manipulation, construction of proto-symbol space and geometric proto-symbol manipulation method are established.

My 3 American Books

English have told me that his translations are on a par with my originals. But I prefer to think they've made my novels better. I admit that some people, with dubious motives, have told me he's added things absent in the original, such as descriptions of sex. These people were ignorant of the fact that he and I have an agreement that he'll translate sex scenes in ways that will appeal to American readers, which is why the English and Chinese versions may seem different. Howard and I began our collaboration in 1988. We've exchanged more than a hundred letters and spoken innumerable times over the telephone. The sole purpose of such frequent contact is to perfect the English translations. Often, we confer over a phrase or an object with which he's unfamiliar. Sometimes, I have to call upon my primitive drawing skills to sketch something for him. From this you can see that he is not only a talented translator, but a serious and conscientious one. It's my good fortune to be able to work with someone like him.

A modular system for robust positioning using feedback from stereo vision

This paper introduces a modular framework for robot motion control using stereo vision. The approach is based on a small number of generic motion control operations referred to as primitive skills. Each primitive skill uses visual feedback to enforce a specific task-space kinematic constraint between a robot end-effector and a set of target features. By observing both the end-effector and target features, primitive skills are able to position with an accuracy that is independent of errors in hand-eye calibration. Furthermore, primitive skills are easily combined to form more complex kinematic constraints as required by different applications. These control laws have been integrated into a system that performs tracking and control on a single processor at real-time rates. Experiments with this system have shown that it is extremely accurate, and that it is insensitive to camera calibration error. The system has been applied to a number of example problems, showing that modular, high precision, vision-based motion control is easily achieved with off-the-shelf hardware.

Intelligence and the epistemics of interpersonal acumen: Testing some implications of Gardner's theory

Gardner (1985) theorized a developmental trajectory leading to qualitative changes in the ability to read motives or intentions, which we viewed as implying stages (or levels) of interpersonal acumen in adults. To test this idea, we conceptualized graduated levels of action-intention combinations ranging from least to most cognitively taxing according to particular end-state skills described by Gardner. In a set of studies using varied formats, we found that, if adult subjects mastered one combination in the hierarchy, they also tended to master combinations implying more primitive skills; if they failed a task, they generally failed at combinations implying more complex skills. We were able to find no substantial relationships between task performance and surrogate indices of verbal and mathematical IQ or standard tests of interpersonal reactivity, interpersonal trust, need for cognition, and self-monitoring. Although tentative, this finding was consistent with Gardner's view of interpersonal intelligence as independent of g-ocentric facets of intellectual potential and different from personality. We isolated a set of self-described markers of high and low scorers, which also seemed consistent with Gardner's intuitions. We conclude by noting some limitations of this investigation.

Comparison of deficits in cognitive and motor skills among children with dyslexia

There is a growing body of evidence that children with dyslexia have problems not just in reading but in a range of skills including several unrelated to reading. In an attempt to compare the severity and incidence of deficits across these varied domains, children with dyslexia (mean ages 8, 12, and 16 years), and control groups of normally achieving children matched for IQ and for age or reading age, were tested on a range of primitive (basic) skills. The children with dyslexia performed significantly worse than the same-age controls on most tasks, and significantly worse even than the reading-age controls on phoneme segmentation, picture naming speed, word tachistoscopic word recognition, speeded bead threading and some balance tasks. The overall performance of the children with dyslexia is interpreted as showing less complete automatization than normal.

Effect of Manipulation of Children's Affect on Their Family-Drawings

Summary Drawing pattern changes elicited following experimental manipulation of young children's self-esteem lent support to the notion that dynamic defensive processes are reflected in drawings. Some global drawing patterns previously identified were used to score drawings because of the primitive drawing skills of the 4- and 5-year-old Ss. Criticism of Ss' toy building capacity elicited drawing patterns of constriction-impoverishment; supportive comments during a play therapy session elicited expansion-improvement. Findings and observations were related to theory of cognitive-defensive style.