Robotic Hardware and Software Integration for Changing Human Intentions

Author(s):  
Akif Durdu ◽  
Ismet Erkmen ◽  
Aydan M. Erkmen ◽  
Alper Yilmaz

Estimating and reshaping human intentions are among the most significant topics of research in the field of human-robot interaction. This chapter provides an overview of intention estimation literature on human-robot interaction, and introduces an approach on how robots can voluntarily reshape estimated intentions. The reshaping of the human intention is achieved by the robots moving in certain directions that have been a priori observed from the interactions of humans with the objects in the scene. Being among the only few studies on intention reshaping, the authors of this chapter exploit spatial information by learning a Hidden Markov Model (HMM) of motion, which is tailored for intelligent robotic interaction. The algorithmic design consists of two phases. At first, the approach detects and tracks human to estimate the current intention. Later, this information is used by autonomous robots that interact with detected human to change the estimated intention. In the tracking and intention estimation phase, postures and locations of the human are monitored by applying low-level video processing methods. In the latter phase, learned HMM models are used to reshape the estimated human intention. This two-phase system is tested on video frames taken from a real human-robot environment. The results obtained using the proposed approach shows promising performance in reshaping of detected intentions.

Robotics ◽  
2013 ◽  
pp. 1381-1406
Author(s):  
Akif Durdu ◽  
Ismet Erkmen ◽  
Aydan M. Erkmen ◽  
Alper Yilmaz

Estimating and reshaping human intentions are among the most significant topics of research in the field of human-robot interaction. This chapter provides an overview of intention estimation literature on human-robot interaction, and introduces an approach on how robots can voluntarily reshape estimated intentions. The reshaping of the human intention is achieved by the robots moving in certain directions that have been a priori observed from the interactions of humans with the objects in the scene. Being among the only few studies on intention reshaping, the authors of this chapter exploit spatial information by learning a Hidden Markov Model (HMM) of motion, which is tailored for intelligent robotic interaction. The algorithmic design consists of two phases. At first, the approach detects and tracks human to estimate the current intention. Later, this information is used by autonomous robots that interact with detected human to change the estimated intention. In the tracking and intention estimation phase, postures and locations of the human are monitored by applying low-level video processing methods. In the latter phase, learned HMM models are used to reshape the estimated human intention. This two-phase system is tested on video frames taken from a real human-robot environment. The results obtained using the proposed approach shows promising performance in reshaping of detected intentions.


1981 ◽  
Vol 59 (1) ◽  
pp. 127-131 ◽  
Author(s):  
Alan N. Campbell

The properties named in the title have been determined by standard methods. Viscosity, molar volume, and orientation polarisation all indicate abnormalities of the nature of association between the components.The most interesting result is that of surface tension which indicates that, in the case of the binary system triethylamine–water, a surface layer of constant composition is formed over a wide range of total composition. When, by a rise in temperature of two or three degrees, this layer becomes unstable, it splits into two phases of different composition. The surface layer may then be instantaneously reformed and so on. A mechanism for the generation of a two-phase system is thus established. The data for the three-phase, isothermal, system are not so convincing, for reasons that are suggested.


1971 ◽  
Vol 125 (1) ◽  
pp. 179-187 ◽  
Author(s):  
M. C. Perry ◽  
W. Tampion ◽  
J. A. Lucy

1. A simple two-phase chloroform–aqueous buffer system was used to investigate the interaction of insulin with phospholipids and other amphipathic substances. 2. The distribution of 125I-labelled insulin in this system was determined after incubation at 37°C. Phosphatidic acid, dicetylphosphoric acid and, to a lesser extent, phosphatidylcholine and cetyltrimethylammonium bromide solubilized 125I-labelled insulin in the chloroform phase, indicating the formation of chloroform-soluble insulin–phospholipid or insulin–amphipath complexes. Phosphatidylethanolamine, sphingomyelin, cholesterol, stearylamine and Triton X-100 were without effect. 3. Formation of insulin–phospholipid complex was confirmed by paper chromatography. 4. The two-phase system was adapted to act as a simple functional system with which to investigate possible effects of insulin on the structural and functional properties of phospholipid micelles in chloroform, by using the distribution of [14C]glucose between the two phases as a monitor of phospholipid–insulin interactions. The ability of phospholipids to solubilize [14C]glucose in chloroform increased in the order phosphatidylcholine<sphingomyelin<phosphatidylethanolamine<phosphatidic acid. Insulin decreased the [14C]glucose solubilized by phosphatidylcholine, phosphatidylethanolamine and phosphatidic acid, but not by sphingomyelin. 5. The significance of these results and the molecular requirements for the formation of insulin–phospholipid complexes in chloroform are discussed.


1976 ◽  
Vol 230 (4) ◽  
pp. 1121-1125 ◽  
Author(s):  
CA Wiederhielm ◽  
Fox ◽  
DR Lee

The osmotic interaction of mucopolysaccharides and plasma proteins, normally present in the interstitium, has been investigated. It has been found that hyaluronate-plasma protein mixtures may be treated as a two-phase system and that the two phases are in osmotic equilibrium. The osmotic pressures exerted by these mixtures are higher than the algebraic sum of the two components. At concentrations normally present in the interstitium of skin and muscle (0.6% mucopolysaccharides and 2% protein), the osmotic pressure exerted by the mixture is on the order of 10 mmHg, which is in agreement with predictions from earlier computer-simulation studies. The partition of fluid between the gel-like mucopolysaccharide compartment and the free-fluid containing the protein is approximately 50% in the "gel" phase at concentrations found in the interstitium. The volume exclusion effects of the interstitial mucopolysaccharides are significant, both in terms of selection of tracer molecules for interstitial volume measurements and also as an osmotic buffering mechanism which aids in maintaining the partition of fluid between the circulation and the interstitial space.


2009 ◽  
Vol 17 (1) ◽  
pp. 3-5
Author(s):  
Stephen W. Carmichael

This is not an article about the song made famous by the late (great) Don Ho. This is about a breakthrough in the understanding of how micrometer-sized bubbles can be stabilized for long periods of time. This can influence the taste, smell, and consistency of consumer products including food and cosmetics.In two-phase systems, which can include air (as bubbles) suspended within a liquid, the structures of the dispersed (bubbles) and continuous (liquid) phases play a critical role in determining the properties of the material. There is also the function of time in that the microstructure of the dispersed phase continuously evolves toward a state of lower energy by minimizing the surface area between the two phases (referred to as the interfacial area). In the long term, this time evolution diminishes the usefulness of two-phase systems. Emilie Dressaire, Rodney Bee, David Bell, Alex Lips, and Howard Stone have devised a way to stabilize a two-phase system for time periods of a year or longer.


2006 ◽  
Vol 16 (04) ◽  
pp. 559-586 ◽  
Author(s):  
MICHEL FRÉMOND ◽  
ELISABETTA ROCCA

The paper deals with a phase transition model applied to a two-phase system. There is a wide literature on the study of phase transition processes in case that no voids nor overlapping can occur between the two phases. The main novelty of our approach is the possibility of having voids during the phase change. This aspect is described in the model by the mass balance equation whose effects are included by means of the pressure of the system in the dynamical relations. The state variables are the absolute temperature (whose evolution is ruled by the entropy balance equation), the strain tensor (satisfying a quasi-static macroscopic equation of motion), and the volume fractions of the two phases (whose evolutions are described by a vectorial equation coming from the principle of virtual power and related to the microscopic motions). Well-posedness of the initial-boundary value problem associated to the PDEs system resulting from this model is proved.


Sign in / Sign up

Export Citation Format

Share Document