Krishnanand N. Kaipa

Toward Safe Human Robot Collaboration by Using Multiple Kinects Based Real-Time Human Tracking

We present a multiple Kinects based exteroceptive sensing framework to achieve safe human-robot collaboration during assembly tasks. Our approach is mainly based on a real-time replication of the human and robot movements inside a physics-based simulation of the work cell. This enables the evaluation of the human-robot separation in a 3D Euclidean space, which can be used to generate safe motion goals for the robot. For this purpose, we develop an N-Kinect system to build an explicit model of the human and a roll-out strategy, in which we forward-simulate the robots trajectory into the near future. Now, we use a precollision strategy that allows a human to operate in close proximity with the robot, while pausing the robots motion whenever an imminent collision between the human model and any part of the robot is detected. Whereas most previous range based methods analyzed the physical separation based on depth data pertaining to 2D projections of robot and human, our approach evaluates the separation in a 3D space based on an explicit human model and a forward physical simulation of the robot. Real-time behavior (≈ 30 Hz) observed during experiments with a 5 DOF articulated robot and a human safely collaborating to perform an assembly task validate our approach.

Improving assembly precedence constraint generation by utilizing motion planning and part interaction clusters

In this paper, we present a technique that combines motion planning and part interaction clusters to improve generation of assembly precedence constraints. In particular, this technique automatically finds, and clusters, parts that can mutually affect each others accessibility, and hence may impose assembly constraints. This enables the generation of accurate precedence constraints without needing to examine all possible assembly sequences. Given an assembly model, our technique generates potential disassembly layers: spatial clustering is used to generate part sets. Next, motion planning based on rapidly-exploring random trees (RRT) with multiple trees is used to evaluate the interaction between these part sets. Specifically, motion planning is used to determine which part sets can be removed from the assembly. These sets are added to the first disassembly layer and removed from the assembly. Part sets that can be removed from the simplified assembly are then added to the second layer. If the process gets stuck, parts in the parent set are regrouped, and the process continues until all disassembly layers are found. The resulting structure reveals precedence relationships among part sets, which can be used to generate feasible assembly sequences for each part set and the whole assembly. We present theoretical results related to the algorithms developed in the paper. Computational results from tests on a variety of assemblies are presented to illustrate our approach.

Resolving automated perception system failures in bin-picking tasks using assistance from remote human operators

We present an approach to resolve automated perception failures during bin-picking operations in hybrid assembly cells. Our model exploits complementary strengths of humans and robots. Whereas the robot performs bin-picking and proceeds to the subsequent operation like kitting or assembly, a remotely located human assists the robot in critical situations by resolving any automated perception problems encountered during bin-picking. We present the design details of our overall system comprising an automated part recognition system and a remote user interface that allows effective information exchange between the human and the robot that is geared toward solutions that minimize human operator time in resolving the detected perception failures. We use illustrative real robot experiments to show that human-robot information exchange leads to improved bin-picking performance.

An ontology to enable optimized task partitioning in human-robot collaboration for warehouse kitting operations

Collaborative teams of human operators and mobile ground robots are becoming popular in manufacturing plants to assist humans with a lot of the repetitive tasks such as the packing of related objects into different units, an operation known as kitting. In this paper, we present an ontology to provide a unified representation of all kitting-related tasks, which are decomposed into atomic actions that are either computational involving sensing, perception, planning, and control, or physical involving actuation and manipulation. The ontology is then used in a stochastic integer linear program for optimum partitioning of the atomic tasks between the robots and humans. Preliminary experiments on a single robot, single human case yield promising results where the kitting operations are completed with lower durations and manipulation failure rates using human-robot partnership versus just the human or only the robot. This success is achieved by the robot seeking human assistance for visual perception tasks while performing the other tasks primarily on its own.

Instruction Generation for Assembly Operations Performed by Humans

This paper presents the design of an instruction generation system that can be used to automatically generate instructions for complex assembly operations performed by humans on factory shop floors. Multimodal information—text, graphical annotations, and 3D animations—is used to create easy-to-follow instructions. This thereby reduces learning time and eliminates the possibility of assembly errors. An automated motion planning subsystem computes a collision-free path for each part from its initial posture in a crowded scene onto its final posture in the current subassembly. Visualization of this computed motion results in generation of 3D animations. The system also consists of an automated part identification module that enables the human to identify, and pick, the correct part from a set of similar looking parts. The system’s ability to automatically translate assembly plans into instructions enables a significant reduction in the time taken to generate instructions and update them in response to design changes.© 2012 ASME

Physics-Aware Informative Coverage Planning for Autonomous Vehicles

Unmanned vehicles are emerging as an attractive tool for persistent monitoring tasks of a given area, but need automated planning capabilities for effective unattended deployment. Such an automated planner needs to generate collision-free coverage paths by steering waypoints to locations that both minimize the path length and maximize the amount of information gathered along the path. The approach presented in this paper significantly extends prior work and handles motion uncertainty of an unmanned vehicle and the presence of obstacles by using a Markov Decision Process based approach to generate collision-free paths. Simulation results show that the proposed approach is robust to significant motion uncertainties and reduces the probability of collision with obstacles in the environment.

A Horseshoe Crab Inspired Surf Zone Robot With Righting Capabilities

In this paper, we present the design of RoboCrab, an amphibious robot capable of traversing moderate surf zone environments. By taking inspiration from the morphology, locomotion, and righting behaviors of a horseshoe crab, the robot is designed for traversal and righting on granular terrain, open water, and turbulent surf zones. We present the details of the crab’s morphology that informed the design of our robot. Next, we present the mechanical design, material selection, and manufacturing of the various parts of the robot. We report the results from the computational fluid dynamics simulations used to characterize the robot shell performance. Finally, we present demonstrations of the physical robot walking and righting in a granular environment.Copyright

Robotic bimanual cleaning of deformable objects with online learning of part and tool models

In this paper, we present an approach to perform automatic robotic cleaning of deformable objects with unknown stiffness characteristics. A bimanual robot setup is used, where one arm holds the part to be cleaned, while the other holds the cleaning tool. The robot maintains an approximate model of the deformation behavior of each part it interacts with and incrementally improves the model as it performs cleaning attempts, thereby gaining information. Simultaneously, the robot maintains a model of the cleaning tool performance which is independent of the particular part and can be learned over multiple episodes of interaction with different parts. During each attempt, the robot exploits its current knowledge of the part deformation behavior to select an optimal set of grasp locations that minimize the amount of deformation. Results indicate the system is able to incrementally learn the deformation model of parts with approximate linear geometry and that the improving model can be quickly used to select the correct grasp locations and tool parameters for rapid cleaning.

Assembly Sequence Planning by Using Multiple Random Trees Based Motion Planning

In this paper, we introduce multiple random trees based motion planning to perform assembly sequence planning for complex assemblies. Initially, given an assembly model, our technique performs disassembly sequence planning. This approach dynamically reduces the size and complexity of the assembly based on a hierarchical exploration structure that keeps information about the completion of the disassembly. Next, the disassembly information is used to generate feasible assembly sequences, along with precedence constraints, to assemble each part into the current subassembly. The motion planning system chooses part order by detecting geometrical interferences and analyzing feasible part movements. Results from tests on a variety of complex assemblies validate the efficiency of our approach.Copyright

Glowworm Swarm Optimization

This book provides a comprehensive account of the glowworm swarm optimization (GSO) algorithm, including details of the underlying ideas, theoretical foundations, algorithm development, various applications, and MATLAB programs for the basic GSO algorithm. It also discusses several research problems at different levels of sophistication that can be attempted by interested researchers. The generality of the GSO algorithm is evident in its application to diverse problems ranging from optimization to robotics. Examples include computation of multiple optima, annual crop planning, cooperative exploration, distributed search, multiple source localization, contaminant boundary mapping, wireless sensor networks, clustering, knapsack, numerical integration, solving fixed point equations, solving systems of nonlinear equations, and engineering design optimization. The book is a valuable resource for researchers as well as graduate and undergraduate students in the area of swarm intelligence and computational intelligence and working on these topics.