Search

Robotic task instructions often involve a referred object that the robot must locate (ground) within the environment. While task intent understanding is an essential part of natural language understanding, less effort is made to resolve ambiguity that may arise while grounding the task. Existing works use vision-based task grounding and ambiguity detection, suitable for a fixed view and a static robot. However, the problem magnifies for a mobile robot, where the ideal view is not known beforehand. Moreover, a single view may not be sufficient to locate all the object instances in the given area, which leads to inaccurate ambiguity detection. Human intervention is helpful only if the robot can convey the kind of ambiguity it is facing. In this article, we present DoRO (Disambiguation of Referred Object), a system that can help an embodied agent to disambiguate the referred object by raising a suitable query whenever required. Given an area where the intended object is, DoRO finds all the instances of the object by aggregating observations from multiple views while exploring & scanning the area. It then raises a suitable query using the information from the grounded object instances. Experiments conducted with the AI2Thor simulator show that DoRO not only detects the ambiguity more accurately but also raises verbose queries with more accurate information from the visual-language grounding., Accepted in IEEE Robotics & Automation Letters (RA-L)

Overmodulation techniques of asymmetrical six-phase machine achieve higher dc-bus utilization by applying voltage in the nonenergy transfer plane. This results into unwanted current and associated copper loss. Existing overmodulation technique minimizes this voltage from space-vector perspective with predefined set of four active vectors. To find the best technique, one needs to perform the above minimization problem with all possible sets of active vectors with which higher voltage gain can be attained. Therefore, this requires evaluation of large number of cases. This article formulates the above minimization problem in terms of average voltage vectors of two three-phase inverters, where active vectors need not to be specified beforehand and, thus, the analysis is more general. Sixteen possible techniques with different set of active vectors are derived following the above analysis, which attain minimum voltage injection in the nonenergy transfer plane. This article also identifies one of these 16 techniques, which can be implemented without involving complex six-dimensional transformation. The above technique is validated through experiments on six-phase induction motor and simulations in MATLAB at 3.5-kW power level.

Overmodulation (OVM) techniques of asymmetrical six-phase induction machine (ASIM) achieve higher dc-bus utilization by applying nonzero average voltage in nonenergy transfer plane. This results into unwanted current and associated copper loss. Existing OVM techniques reduce this loss with pulsewidth modulation (PWM) techniques from six-dimensional space vector perspective, which is both conceptually difficult and computationally challenging. The computational complexity of space vector based techniques is reduced by few existing PWM techniques in linear region by splitting the six-phase inverter as two three-phase inverters and modulate these inverters with linear PWM techniques in 30 $^\circ$ phase shifted. This is referred as three-phase inverter based technique in the title. But, three-phase inverter based OVM technique does not exist in the literature due to lack of knowledge of the relationship between six-dimensional space vectors and space vectors of two three-phase inverters. This article first establishes this relation. Based on this relation, an OVM technique is proposed where the reference voltage vectors of two inverters are phase shifted by 30 $^\circ$ but of different magnitudes. The proposed technique achieves THD and WTHD performances similar to space vector based best technique of ASIM with reduced computational complexity, as shown in details. The proposed strategy is validated through experiments and simulations on six-phase induction machine at 4.2 kW.

Bin packing using a robotic arm is an important problem in the context of Industry 4.0. In this work, we present a reliable and efficient bin packing system, called Jampacker . We propose a new offline 3D bin packing algorithm, called Jampack that achieves higher packing efficiency in comparison to the state-of-the-art algorithms. Jampack computes placement points, called internal corner points that tries to maximize the utilization of free spaces in-between objects, which are generally ignored by existing algorithms. Additionally, we introduce a fault recovery module (FRM) for the robotic manipulator that helps to achieve a more reliable and efficient packing in a physical container. The FRM module monitors the object placement by the robotic arm, calculates a fault score for the placement, adjusts the placement if required, and also learns & adjusts the offset for the placement procedure on-the-go. We show that this system achieves faster completion of the overall packing process.

Linear modulation techniques (LMTs) of an asymmetrical six-phase machine (ASPM) with two isolated neutral points synthesize the desired voltage vectors by applying at least five switching states. Different choices of applied voltage vectors, sequences in which they are used, distribution of dwell times among the redundant switching states give rise to a large number of possible LMTs. It is desirable that these LMTs avoid more than two transitions of a particular inverter leg within a carrier period. Only a subset of existing LMTs of ASPM follows this rule. Through an innovative approach, this paper finds a way to account for all possible infinitely many LMTs that follow the rule of at most two transitions per leg. Another important criterion for the selection of an LMT is its current-ripple performance. Therefore, through numerical optimization, the paper finds optimal LMTs among the above infinite possible LMTs for all reference voltage vectors in the linear range and for the whole feasible range of a machine parameter. This parameter is related to the leakage inductance of the machine and impacts the current ripple performance of ASPM. An optimal hybrid strategy is proposed with these optimal techniques, which outperforms all existing techniques in terms of the current ripple. The theoretical analysis is validated through simulation in Matlab and experiments performed up to 3.5 kW on a hardware prototype.