Towards vision-based deep reinforcement learning for robotic motion control

This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real hardware and real observation in a naive approach failed, but experiments show that the network works when replacing camera images with synthetic images.

Coordination Behaviour of Imino Hydrazone Ligands towards Nickel (II) and Copper (II) Ions

The complexing ability of a new series of ligands, β-N-arylimine hydrazones, toward Ni (II) and Cu (II) ions has been studied. The isolated complexes are characterised on the basis of elemental analysis, spectroscopic methods and magnetic susceptibility measurements. The ligands are notentially bidentate in character coordinating to divalent metal ions through the N1 and N5 nitrogens. Square planar geometry of the metal ions is suggested on the basis of experimental evidence.

Spectroscopic and Coordination Behavior of α-Cyanothioacetamide

α-Cyanothioacetamide (CTAM) complexes of cuprous chloride CuCl–2CTAM and cuprous bromide CuBr–2CTAM have been prepared. The infrared spectra of CTAM and its complexes, and the laser Raman spectrum of CTAM have been recorded. Assignment of the frequencies of the ligand has been made on the basis of a normal coordinate analysis using the Urey-Bradley force field. The copper (I) complexes are inferred to have thiocarbonyl sulfur and amide nitrogen bonded CTAM as evidenced from infrared and electronic spectra.

Coordination and plasticity in leaf anatomical traits of invasive and native vine species

Premise of the study: Plant invasiveness can be promoted by higher values of adaptive traits (e.g., photosynthetic capacity, biomass accumulation), greater plasticity and coordination of these traits, and by higher and positive relative influence of these functionalities on fitness, such as increasing reproductive output. However, the data set for this premise rarely includes linkages between epidermal–stomatal traits, leaf internal anatomy, and physiological performance.• Methods: Three ecological pairs of invasive vs. noninvasive (native) woody vine species of South-East Queensland, Australia were investigated for trait differences in leaf morphology and anatomy under varying light intensity. The linkages of these traits with physiological performance (e.g., water-use efficiency, photosynthesis, and leaf construction cost) and plant adaptive traits of specific leaf area, biomass, and relative growth rates were also explored.• Key results: Except for stomatal size, mean leaf anatomical traits differed significantly between the two groups. Plasticity of traits and, to a very limited extent, their phenotypic integration were higher in the invasive relative to the native species. ANOVA, ordination, and analysis of similarity suggest that for leaf morphology and anatomy, the three functional strategies contribute to the differences between the two groups in the order phenotypic plasticity > trait means > phenotypic integration.• Conclusions: The linkages demonstrated in the study between stomatal complex/gross anatomy and physiology are scarce in the ecological literature of plant invasiveness, but the findings suggest that leaf anatomical traits need to be considered routinely as part of weed species assessment and in the worldwide leaf economic spectrum.

Ambidentate coordination of isonitrosoacetylacetone imines in their nickel(II) and palladium(II) complexes

Nickel(I1) and palladium(I1) complexes of the types Ni(R-IAI)(IAI'), Pd(IAI)(IAI'), and Pd(R-IAI), , where IAI and IAI' represent isonitrosoacetylacetone imine and R-IAI represents its Aralkyl derivative, have been prepared. The molar conductance, molecular weight, magnetic moment, and ir, pmr, and electronic spectra of these com- plexes have been studied. It is suggested that the isonitroso group of R-IAI coordinates through the nitrogen and that of IAI' thiough the oxygen in Ni(R-IAI)(IAI'). In Pd(R-IAI), the isonitroso groups of both ligands coordinate through nitrogen while Pd(IAI)(IAI') has a structure similar to that of Ni(R-IAI)(IAI'). The amine- exchange reactions of nickel(I1) and palladium(I1) complexes are discussed and compared on the basis of their structures.

Coordination properties of vic-isonitrosoimines in their copper (II) and palladium (II) complexes

Preparation and structural characterization of palladium (II) complexes of ligands III-V and copper (II) complexes of III are reported. The elemental analyses of the complexes show that the metal: ligand ratio is 1 : 2. The electrical conductance in acetone shows the non-electrolytic nature of the complexes. The diamagnetic character suggests a gross square-planar geometry for the palladium (II) complexes. Copper (II) complexes are paramagnetic with/~eff.~l'90 B.M. Spectral data suggest that in all the complexes the ligand coordinates to the metal (II) symmetrically through isonitroso-nitrogen and imine-nitrogen, forming a ¡ membered chelate ring. Amine-exchange reactions of the complexes are discussed and compared on the basis of their structures.

Activities of daily living in children with developmental coordination disorder: Performance, learning, and participation

Background Children with developmental coordination disorder (DCD) face evident motor difficulties in daily functioning. Little is known, however, about their difficulties in specific activities of daily living (ADL). Objective The purposes of this study were: (1) to investigate differences between children with DCD and their peers with typical development for ADL performance, learning, and participation, and (2) to explore the predictive values of these aspects. Design. This was a cross-sectional study. Methods In both a clinical sample of children diagnosed with DCD (n=25 [21 male, 4 female], age range=5-8 years) and a group of peers with typical development (25 matched controls), the children’s parents completed the DCDDaily-Q. Differences in scores between the groups were investigated using t tests for performance and participation and Pearson chi-square analysis for learning. Multiple regression analyses were performed to explore the predictive values of performance, learning, and participation. Results Compared with their peers, children with DCD showed poor performance of ADL and less frequent participation in some ADL. Children with DCD demonstrated heterogeneous patterns of performance (poor in 10%-80% of the items) and learning (delayed in 0%-100% of the items). In the DCD group, delays in learning of ADL were a predictor for poor performance of ADL, and poor performance of ADL was a predictor for less frequent participation in ADL compared with the control group. Limitations A limited number of children with DCD were addressed in this study. Conclusions This study highlights the impact of DCD on children’s daily lives and the need for tailored intervention.

Development and psychometric properties of the DCDDaily: a new test for clinical assessment of capacity in activities of daily living in children with developmental coordination disorder

Objective To develop the DCDDaily, an instrument for objective and standardized clinical assessment of capacity in activities of daily living (ADL) in children with developmental coordination disorder (DCD), and to investigate its usability, reliability, and validity. Subjects Five to eight-year-old children with and without DCD. Main measures The DCDDaily was developed based on thorough review of the literature and extensive expert involvement. To investigate the usability (assessment time and feasibility), reliability (internal consistency and repeatability), and validity (concurrent and discriminant validity) of the DCDDaily, children were assessed with the DCDDaily and the Movement Assessment Battery for Children-2 Test, and their parents filled in the Movement Assessment Battery for Children-2 Checklist and Developmental Coordination Disorder Questionnaire. Results 459 children were assessed (DCD group, n = 55; normative reference group, n = 404). Assessment was possible within 30 minutes and in any clinical setting. For internal consistency, Cronbach’s α = 0.83. Intraclass correlation = 0.87 for test–retest reliability and 0.89 for inter-rater reliability. Concurrent correlations with Movement Assessment Battery for Children-2 Test and questionnaires were ρ = −0.494, 0.239, and −0.284, p < 0.001. Discriminant validity measures showed significantly worse performance in the DCD group than in the control group (mean (SD) score 33 (5.6) versus 26 (4.3), p < 0.001). The area under curve characteristic = 0.872, sensitivity and specificity were 80%. Conclusions The DCDDaily is a valid and reliable instrument for clinical assessment of capacity in ADL, that is feasible for use in clinical practice.

Lanthanide coordination in dimethyl sulphoxide and antipyrine complexes of rare earth nitrates

Abstract is not available.

Synthesis of a one-dimensional coordination polymer containing pendant hydrosulfide groups

In view of the recent interest in compounds containing M-SH units, an organotin hydrosulfide compound, Me2Sn(SH)(O2CMe) (1) was prepared by controlled hydrolysis of the diorganotin thioacetate. Under similar mild hydrolytic conditions the corresponding benzoate could not be isolated. Instead, the thiobenzoate complex, Me2Sn(SOCPh)(2) (3) was obtained in excellent yields indicating that there was no hydrolysis. Both 1 and 3 were characterized by X-ray crystallography. Some properties of the polymeric compound 1, such as spectral, electrical conductivity and NLO response were also studied. The reactivity and properties were explained using density functional calculations.

A Distributed Robotic Vision Service

Robotic vision is limited by line of sight and onboard camera capabilities. Robots can acquire video or images from remote cameras, but processing additional data has a computational burden. This paper applies the Distributed Robotic Vision Service, DRVS, to robot path planning using data outside line-of-sight of the robot. DRVS implements a distributed visual object detection service to distributes the computation to remote camera nodes with processing capabilities. Robots request task-specific object detection from DRVS by specifying a geographic region of interest and object type. The remote camera nodes perform the visual processing and send the high-level object information to the robot. Additionally, DRVS relieves robots of sensor discovery by dynamically distributing object detection requests to remote camera nodes. Tested over two different indoor path planning tasks DRVS showed dramatic reduction in mobile robot compute load and wireless network utilization.

Find my office: Navigating real space from semantic descriptions

This paper shows that by using only symbolic language phrases, a mobile robot can purposefully navigate to specified rooms in previously unexplored environments. The robot intelligently organises a symbolic language description of the unseen environment and “imagines” a representative map, called the abstract map. The abstract map is an internal representation of the topological structure and spatial layout of symbolically defined locations. To perform goal-directed exploration, the abstract map creates a high-level semantic plan to reason about spaces beyond the robot’s known world. While completing the plan, the robot uses the metric guidance provided by a spatial layout, and grounded observations of door labels, to efficiently guide its navigation. The system is shown to complete exploration in unexplored spaces by travelling only 13.3% further than the optimal path.

Development of a robust framework for an outdoor mobile manipulation UAV

There is a growing interest to autonomously collect or manipulate objects in remote or unknown environments, such as mountains, gullies, bush-land, or rough terrain. There are several limitations of conventional methods using manned or remotely controlled aircraft. The capability of small Unmanned Aerial Vehicles (UAV) used in parallel with robotic manipulators could overcome some of these limitations. By enabling the autonomous exploration of both naturally hazardous environments, or areas which are biologically, chemically, or radioactively contaminated, it is possible to collect samples and data from such environments without directly exposing personnel to such risks. This paper covers the design, integration, and initial testing of a framework for outdoor mobile manipulation UAV. The framework is designed to allow further integration and testing of complex control theories, with the capability to operate outdoors in unknown environments. The results obtained act as a reference for the effectiveness of the integrated sensors and low-level control methods used for the preliminary testing, as well as identifying the key technologies needed for the development of an outdoor capable system.

Uncertainty based online planning for UAV target finding in cluttered and GPS-denied environments

There are some scenarios in which Unmmaned Aerial Vehicle (UAV) navigation becomes a challenge due to the occlusion of GPS systems signal, the presence of obstacles and constraints in the space in which a UAV operates. An additional challenge is presented when a target whose location is unknown must be found within a confined space. In this paper we present a UAV navigation and target finding mission, modelled as a Partially Observable Markov Decision Process (POMDP) using a state-of-the-art online solver in a real scenario using a low cost commercial multi rotor UAV and a modular system architecture running under the Robotic Operative System (ROS). Using POMDP has several advantages to conventional approaches as they take into account uncertainties in sensor information. We present a framework for testing the mission with simulation tests and real flight tests in which we model the system dynamics and motion and perception uncertainties. The system uses a quad-copter aircraft with an board downwards looking camera without the need of GPS systems while avoiding obstacles within a confined area. Results indicate that the system has 100% success rate in simulation and 80% rate during flight test for finding targets located at different locations.

Nuclear quadrupole resonance in coordination compounds

Abstract is not available.