arXiv subjects

Konstantinos Karydis

Publications and source records attributed to Konstantinos Karydis.

66 records · Page 4Linked to original sources

arXiv2021

Enhancement for Robustness of Koopman Operator-based Data-driven Mobile Robotic Systems

Koopman operator theory has served as the basis to extract dynamics for nonlinear system modeling and control across settings, including non-holonomic mobile robot control. There is a growing interest in research to derive robustness (and/or safety) guarantees for systems the dynamics of which are extracted via the Koopman operator. In this paper, we propose a way to quantify the prediction error because of noisy measurements when the Koopman operator is approximated via Extended Dynamic Mode Decomposition. We further develop an enhanced robot control strategy to endow robustness to a class of data-driven (robotic) systems that rely on Koopman operator theory, and we show how part of the strategy can happen offline in an effort to make our algorithm capable of real-time implementation. We perform a parametric study to evaluate the (theoretical) performance of the algorithm using a Van der Pol oscillator and conduct a series of simulated experiments in Gazebo using a non-holonomic wheeled robot.

cs.RO↗

arXiv2021

Task Planning on Stochastic Aisle Graphs for Precision Agriculture

This work addresses task planning under uncertainty for precision agriculture applications whereby task costs are uncertain and the gain of completing a task is proportional to resource consumption (such as water consumption in precision irrigation). The goal is to complete all tasks while prioritizing those that are more urgent, and subject to diverse budget thresholds and stochastic costs for tasks. To describe agriculture-related environments that incorporate stochastic costs to complete tasks, a new Stochastic-Vertex-Cost Aisle Graph (SAG) is introduced. Then, a task allocation algorithm, termed Next-Best-Action Planning (NBA-P), is proposed. NBA-P utilizes the underlying structure enabled by SAG, and tackles the task planning problem by simultaneously determining the optimal tasks to perform and an optimal time to exit (i.e. return to a base station), at run-time. The proposed approach is tested with both simulated data and real-world experimental datasets collected in a commercial vineyard, in both single- and multi-robot scenarios. In all cases, NBA-P outperforms other evaluated methods in terms of return per visited vertex, wasted resources resulting from aborted tasks (i.e. when a budget threshold is exceeded), and total visited vertices.

cs.RO↗

arXiv2020

A Data-driven Hierarchical Control Structure for Systems with Uncertainty

The paper introduces a Data-driven Hierarchical Control (DHC) structure to improve performance of systems operating under the effect of system and/or environment uncertainty. The proposed hierarchical approach consists of two parts: 1) A data-driven model identification component to learn a linear approximation between reference signals given to an existing lower-level controller and uncertain time-varying plant outputs. 2) A higher-level controller component that utilizes the identified approximation and wraps around the existing controller for the system to handle modeling errors and environment uncertainties during system deployment. We derive loose and tight bounds for the identified approximation's sensitivity to noisy data. Further, we show that adding the higher-level controller maintains the original system's stability. A benefit of the proposed approach is that it requires only a small amount of observations on states and inputs, and it thus works online; that feature makes our approach appealing to robotics applications where real-time operation is critical. The efficacy of the DHC structure is demonstrated in simulation and is validated experimentally using aerial robots with approximately-known mass and moment of inertia parameters and that operate under the influence of ground effect.

eess.SY↗

arXiv2020

Motion Planning for Collision-resilient Mobile Robots in Obstacle-cluttered Unknown Environments with Risk Reward Trade-offs

Collision avoidance in unknown obstacle-cluttered environments may not always be feasible. This paper focuses on an emerging paradigm shift in which potential collisions with the environment can be harnessed instead of being avoided altogether. To this end, we introduce a new sampling-based online planning algorithm that can explicitly handle the risk of colliding with the environment and can switch between collision avoidance and collision exploitation. Central to the planner's capabilities is a novel joint optimization function that evaluates the effect of possible collisions using a reflection model. This way, the planner can make deliberate decisions to collide with the environment if such collision is expected to help the robot make progress toward its goal. To make the algorithm online, we present a state expansion pruning technique that significantly reduces the search space while ensuring completeness. The proposed algorithm is evaluated experimentally with a built-in-house holonomic wheeled robot that can withstand collisions. We perform an extensive parametric study to investigate trade-offs between (user-tuned) levels of risk, deliberate collision decision making, and trajectory statistics such as time to reach the goal and path length.

cs.RO↗

arXiv2020

Development and Testing of a Novel Automated Insect Capture Module for Sample Collection and Transfer

There exists an urgent need for efficient tools in disease surveillance to help model and predict the spread of disease. The transmission of insect-borne diseases poses a serious concern to public health officials and the medical and research community at large. In the modeling of this spread, we face bottlenecks in (1) the frequency at which we are able to sample insect vectors in environments that are prone to propagating disease, (2) manual labor needed to set up and retrieve surveillance devices like traps, and (3) the return time in analyzing insect samples and determining if an infectious disease is spreading in a region. To help address these bottlenecks, we present in this paper the design, fabrication, and testing of a novel automated insect capture module (ICM) or trap that aims to improve the rate of transferring samples collected from the environment via aerial robots. The ICM features an ultraviolet light attractant, passive capture mechanism, panels which can open and close for access to insects, and a small onboard computer for automated operation and data logging. At the same time, the ICM is designed to be accessible; it is small-scale, lightweight and low-cost, and can be integrated with commercially available aerial robots. Indoor and outdoor experimentation validates ICM's feasibility in insect capturing and safe transportation. The device can help bring us one step closer toward achieving fully autonomous and scalable epidemiology by leveraging autonomous robots technology to aid the medical and research community.

cs.RO↗

arXiv2020

Online Exploration and Coverage Planning in Unknown Obstacle-Cluttered Environments

Online coverage planning can be useful in applications like field monitoring and search and rescue. Without prior information of the environment, achieving resolution-complete coverage considering the non-holonomic mobility constraints in commonly-used vehicles (e.g., wheeled robots) remains a challenge. In this paper, we propose a hierarchical, hex-decomposition-based coverage planning algorithm for unknown, obstacle-cluttered environments. The proposed approach ensures resolution-complete coverage, can be tuned to achieve fast exploration, and plans smooth paths for Dubins vehicles to follow at constant velocity in real-time. Gazebo simulations and hardware experiments with a non-holonomic wheeled robot show that our approach can successfully tradeoff between coverage and exploration speed and can outperform existing online coverage algorithms in terms of total covered area or exploration speed according to how it is tuned.

cs.RO↗

arXiv2019

OpenRoACH: A Durable Open-Source Hexapedal Platform with Onboard Robot Operating System (ROS)

OpenRoACH is a 15-cm 200-gram self-contained hexapedal robot with an onboard single-board computer. To our knowledge, it is the smallest legged robot with the capability of running the Robot Operating System (ROS) onboard. The robot is fully open sourced, uses accessible materials and off-the-shelf electronic components, can be fabricated with benchtop fast-prototyping machines such as a laser cutter and a 3D printer, and can be assembled by one person within two hours. Its sensory capacity has been tested with gyroscopes, accelerometers, Beacon sensors, color vision sensors, linescan sensors and cameras. It is low-cost within \$150 including structure materials, motors, electronics, and a battery. The capabilities of OpenRoACH are demonstrated with multi-surface walking and running, 24-hour continuous walking burn-ins, carrying 200-gram dynamic payloads and 800-gram static payloads, and ROS control of steering based on camera feedback. Information and files related to mechanical design, fabrication, assembly, electronics, and control algorithms are all publicly available on https://wiki.eecs.berkeley.edu/biomimetics/Main/OpenRoACH.

cs.RO↗

arXiv2018

Memory Augmented Control Networks

Planning problems in partially observable environments cannot be solved directly with convolutional networks and require some form of memory. But, even memory networks with sophisticated addressing schemes are unable to learn intelligent reasoning satisfactorily due to the complexity of simultaneously learning to access memory and plan. To mitigate these challenges we introduce the Memory Augmented Control Network (MACN). The proposed network architecture consists of three main parts. The first part uses convolutions to extract features and the second part uses a neural network-based planning module to pre-plan in the environment. The third part uses a network controller that learns to store those specific instances of past information that are necessary for planning. The performance of the network is evaluated in discrete grid world environments for path planning in the presence of simple and complex obstacles. We show that our network learns to plan and can generalize to new environments.

cs.AI↗

arXiv2017

Fast, Autonomous Flight in GPS-Denied and Cluttered Environments

One of the most challenging tasks for a flying robot is to autonomously navigate between target locations quickly and reliably while avoiding obstacles in its path, and with little to no a-priori knowledge of the operating environment. This challenge is addressed in the present paper. We describe the system design and software architecture of our proposed solution, and showcase how all the distinct components can be integrated to enable smooth robot operation. We provide critical insight on hardware and software component selection and development, and present results from extensive experimental testing in real-world warehouse environments. Experimental testing reveals that our proposed solution can deliver fast and robust aerial robot autonomous navigation in cluttered, GPS-denied environments.

cs.RO↗

arXiv2017

End-to-End Navigation in Unknown Environments using Neural Networks

We investigate how a neural network can learn perception actions loops for navigation in unknown environments. Specifically, we consider how to learn to navigate in environments populated with cul-de-sacs that represent convex local minima that the robot could fall into instead of finding a set of feasible actions that take it to the goal. Traditional methods rely on maintaining a global map to solve the problem of over coming a long cul-de-sac. However, due to errors induced from local and global drift, it is highly challenging to maintain such a map for long periods of time. One way to mitigate this problem is by using learning techniques that do not rely on hand engineered map representations and instead output appropriate control policies directly from their sensory input. We first demonstrate that such a problem cannot be solved directly by deep reinforcement learning due to the sparse reward structure of the environment. Further, we demonstrate that deep supervised learning also cannot be used directly to solve this problem. We then investigate network models that offer a combination of reinforcement learning and supervised learning and highlight the significance of adding fully differentiable memory units to such networks. We evaluate our networks on their ability to generalize to new environments and show that adding memory to such networks offers huge jumps in performance

cs.RO↗

arXiv2017

Neural Network Memory Architectures for Autonomous Robot Navigation

This paper highlights the significance of including memory structures in neural networks when the latter are used to learn perception-action loops for autonomous robot navigation. Traditional navigation approaches rely on global maps of the environment to overcome cul-de-sacs and plan feasible motions. Yet, maintaining an accurate global map may be challenging in real-world settings. A possible way to mitigate this limitation is to use learning techniques that forgo hand-engineered map representations and infer appropriate control responses directly from sensed information. An important but unexplored aspect of such approaches is the effect of memory on their performance. This work is a first thorough study of memory structures for deep-neural-network-based robot navigation, and offers novel tools to train such networks from supervision and quantify their ability to generalize to unseen scenarios. We analyze the separation and generalization abilities of feedforward, long short-term memory, and differentiable neural computer networks. We introduce a new method to evaluate the generalization ability by estimating the VC-dimension of networks with a final linear readout layer. We validate that the VC estimates are good predictors of actual test performance. The reported method can be applied to deep learning problems beyond robotics.

cs.RO↗

arXiv2012

Symbolic Planning and Control Using Game Theory and Grammatical Inference

This paper presents an approach that brings together game theory with grammatical inference and discrete abstractions in order to synthesize control strategies for hybrid dynamical systems performing tasks in partially unknown but rule-governed adversarial environments. The combined formulation guarantees that a system specification is met if (a) the true model of the environment is in the class of models inferable from a positive presentation, (b) a characteristic sample is observed, and (c) the task specification is satisfiable given the capabilities of the system (agent) and the environment.

cs.RO↗