Abstract

Performing dual arm coordinated (reachability)tasks in humanoid robots require complex planning strategies and this complexity increases further, in case of humanoids with articulated torso. These complex strategies may not be suitable for online motion planning. This paper proposes a faster way to accomplish dual arm coordinated tasks using methodology based on Reinforcement Learning. The contribution of this paper is twofold. Firstly, we propose DiGrad (Differential Gradients), a new RL framework for multi-task learning in manipulators. Secondly, we show how this framework can be adopted to learn dual arm coordination in a 27 degrees of freedom (DOF)humanoid robot with articulated spine. The proposed framework and methodology are evaluated in various environments and simulation results are presented. A comparative study of DiGrad with its parent algorithm in different settings is also presented

Abstract

The concept of discrete-time higher order sliding mode (DHOSM) has received increased attention. However, because of the dearth of knowledge on bound of the external disturbance in the system, an adaptive control law is desirable. This brief presents a technique to design a DHOSM control with adaptive switching gains where the bound on the disturbance is considered to be unknown.

Abstract

One of the major issues in an interconnected power system is the low damping of inter-area oscillations. A proportional-derivative (PD) compensator is a popular control method which is extensively being used as an active damping control in various domains such as robotics, smart structure, etc. However, existence of noise in wide-area signal makes an ideal PD compensator unrealisable in power systems. In this endeavour, a new methodology christened as time-delayed control is proposed where artificial delay is used to provide derivative action which acts as a damping component of wide-area controller. The delay margin is computed for the closed loop system using Razumikhin approach. It is observed that the proposed controller is able to damp the oscillations adequately with reduced sensitivity to the noise in the signals. Further, the proposed controller is able to provide robustness against uncertainties arising from the system dynamics and inherent delay in communication channel.

Abstract

In this paper, a new Adaptive Sliding Mode Control (ASMC) framework is proposed for the tracking control of a class of uncertain nonlinear systems where system states are present explicitly in the upper bound of the overall (or lumped) system uncertainty. Conventional ASMC strategies presume that either the overall (or lumped) uncertainty of the system or its time derivative is norm bounded by a constant. However, such assumption restricts the evaluation of the states a priori for the class of systems that has been considered in this paper. The proposed ASMC law does not presume such constant upper bound on the system uncertainties and, rather, exploits the unique structure of the uncertainty bound to design the control law. Moreover, the adaptive law of the proposed ASMC alleviates the overestimation-underestimation problems of switching gain which is commonly observed in the existing ASMC laws. Simulation results using a two-link manipulator demonstrate improved control performance of the proposed controller in comparison to the conventional ASMC.

Abstract

Preablative stimulated thyroglobulin (ps‑Tg) is an important investigation in the follow‑up of patients with Differentiated thyroid cancer(DTC) after surgery. Levels of ps‑Tg >2–10 ng/ml have been suggested to predict metastasis to cervical and extracervical sites. There is still debate on the need for routine iodine whole‑body scan (131I WBS) in the management of low‑to‑intermediate‑risk DTC patients. Objective: We analyzed our data of patients with DTC who underwent total thyroidectomy to discuss the predictability of ps‑Tg on metastatic disease on the 131I WBS. Materials and Methods: Retrospective analysis of patient records. Results: One hundred and seventeen patients with DTC (95 papillary thyroid cancer [71 had classic histology, 8 had tall cell variant, 16 had follicular variant] and 22 follicular thyroid cancer [18 minimally invasive, 2 hurtle cell, and 2 widely invasive cancers]) had undergone total thyroidectomy. All these patients underwent ps‑Tg assessment and an 131I WBS. About 65% of them went on to have radioiodine ablation along with a posttherapy 131I WBS. We divided the cohort into four groups based on their ps‑Tg levels: Group 1 (ps‑Tg <1), Group 2 (ps‑Tg 1–1.9), Group 3 (ps‑Tg 2–5), and Group 4 (ps‑Tg >5). None of the patients in Group 1, 7% of those combined in Groups 2 and 3 (2 out of 28 patients), and 26% (12 out of 47) of those in Group 4 had either cervical or extracervical metastasis. Those with extracervical metastatic disease to lungs and bones had a mean (standard deviation) ps‑Tg value of 436 (130) and median of 500 ng/ml and those with cervical metastatic disease had a mean Tg value of 31 (64) and median 6.6 ng/ml. Conclusions: A ps‑Tg value in the absence of anti‑Tgantibodies <1 ng/ml reliably excludes metastatic disease in DTC, while a value >5 ng/ml has a 26% risk of having either cervical or extracervical metastasis.

Abstract

Efficient discovery of interesting patterns using parallel algorithms is an actively studied topic in data mining. A key research issue related to this topic is data segmentation, which influences the overall computational requirements of an algorithm. This paper makes an effort to address this issue in correlated pattern mining. Two novel data segmentation techniques, ‘database segmentation’ and ‘transaction segmentation,’ have been introduced to discover the patterns efficiently. The former technique involves segmenting the database into multiple sub-databases such that each sub-database can be mined independently. The latter technique involves segmenting a transaction into multiple sub-transactions such that each sub-transaction can be processed as an individual transaction. The proposed techniques are algorithm independent, and therefore, can be incorporated into any parallel algorithm to find correlated patterns effectively. In this paper, we introduce map-reduce based pattern-growth algorithm by incorporating the above mentioned techniques. Experimental results demonstrate that the proposed algorithm is memory and runtime efficient and highly scalable as well.

Abstract

Weighted Frequent Itemset (WFI) mining is an important model in data mining. The popular adoption and successful industrial application of this model has been hindered by the following two obstacles: (i) finding WFIs is a computationally expensiveness process as these itemsets do not satisfy the downward closure property and (ii) lack of parallel algorithms to find WFIs in very large databases (e.g. astronomical data and twitter data). This paper makes an effort to address these two obstacles. Two pattern-growth algorithms, Sequential Weighted Frequent Pattern-growth and Parallel Weighted Frequent Pattern-growth, have been introduced to discover WFIs efficiently. Both algorithms employ three novel pruning techniques to reduce the computational cost effectively. The first pruning technique prunes some of the uninteresting items by employing a criterion known as cutoff weight. The second pruning technique, called conditional pattern base elimination, eliminates the construction of conditional pattern bases if a suffix item is an uninteresting item. The third pruning technique, called pattern-growth termination, defines a new terminating condition for the pattern-growth technique. Experimental results demonstrate that the proposed algorithms are memory and runtime efficient, and highly scalable as well.

Abstract

A professional player's expertise rests on the ability to predict action by optimally extracting the opponent's postural cues. Eye tracking (head-mounted system) data in a naturalistic singles badminton play was collected from one professional wor0ld-ranked player facing five amateur players (10 serves or 50 trials) and two amateurs playing against four other amateur players each (10 serves or 80 trials). The visual gaze on the opponent body, segregated into 3 areas-of-interest covering the feet, face/torso, and hand/racket of the opponent and the shuttle, was analysed for a) the period just before the serve, b) while receiving the serve and c) the entire rally. The comparative analysis shows the first area-of-interest for professional player as the opponent's feet while executing the serve and the hand/racket when receiving a serve. On the other hand, the amateur players show no particular strategy of fixation location either for the serve task or while facing a serve. The average fixation duration (just before serve) for the professional was 0.96s and for the amateurs it was 1.48s. The findings highlight the differences in the postural cue considered important and the preparatory time in professional and amateur players. We believe, analytical models from dynamic gaze behavior in naturalistic game conditions as applied in this study can be used for enhancing perceptual-cognitive skills during training.

Abstract

Efficacy of games aslearning medium is of interest to researchers and the gaming industry. A critical metric for learning is knowledge retention and very few studies have conducted in-depth comparisons of: a) game versus no-game learning, b) collaborative versus individual learning. Towards this, the study reported in this article will present the findings from an experiment using Asia and world maps, cut into pieces as in a jigsaw puzzle. The participants were primary school children who were randomly assigned to the puzzle and no-puzzle group. To understand the role of collaborative interactions in learning, each group was further divided into two subgroups. Each subgroup either solved the puzzle or studied the full map (no-puzzle) individually or collaboratively. Three post-tests were conducted over a period of 10 days. The mean scores and Mann Whitney test shows: a) In the no-puzzle condition, no difference in the average scores of the individual and collaborative groups for both maps was observed, b) In the puzzle condition, the collaborative group score was slightly more than that of the individual group for Asia map, while the difference was significant for the continent map, and c) Puzzle and no-puzzle individual group scores were comparative for Asia map but the continent map groups showed a major difference. The findings are mixed with collaborative puzzle solving showing higher retention while puzzle solving does not show significant effect on learning and retention.

Abstract

In this work, we consider the problem of decentralized multi-robot target tracking and obstacle avoidance in dynamic environments. Each robot executes a local motion planning algorithm which is based on model predictive control (MPC). The planner is designed as a quadratic program, subject to constraints on robot dynamics and obstacle avoidance. Repulsive potential field functions are employed to avoid obstacles. The novelty of our approach lies in embedding these non-linear potential field functions as constraints within a convex optimization framework. Our method convexifies nonconvex constraints and dependencies, by replacing them as pre-computed external input forces in robot dynamics. The proposed algorithm additionally incorporates different methods to avoid field local minima problems associated with using potential field functions in planning. The motion planner does not enforce predefined trajectories or any formation geometry on the robots and is a comprehensive solution for cooperative obstacle avoidance in the context of multi-robot target tracking. We perform simulation studies for different scenarios to showcase the convergence and efficacy of the proposed algorithm.