Visual Guidance of Unmanned Aerial Manipulators

Abstract

The ability to fly has greatly expanded the possibilities for robots to perform surveillance, inspection or map generation tasks. Yet it was only in recent years that research in aerial robotics was mature enough to allow active interactions with the environment. The robots responsible for these interactions are called aerial manipulators and usually combine a multirotor platform and one or more robotic arms. The main objective of this thesis is to formalize the concept of aerial manipulator and present guidance methods, using visual information, to provide them with autonomous functionalities. A key competence to control an aerial manipulator is the ability to localize it in the environment. Traditionally, this localization has required external infrastructure of sensors (e.g., GPS or IR cameras), restricting the real applications. Furthermore, localization methods with on-board sensors, exported from other robotics fields such as simultaneous localization and mapping (SLAM), require large computational units becoming a handicap in vehicles where size, load, and power consumption are important restrictions. In this regard, this thesis proposes a method to estimate the state of the vehicle (i.e., position, orientation, velocity and acceleration) by means of on-board, low-cost, lightweight and high-rate sensors. With the physical complexity of these robots, it is required to use advanced control techniques during navigation. Thanks to their redundancy on degrees-of-freedom, they offer the possibility to accomplish not only with mobility requirements but with other tasks simultaneously and hierarchically, prioritizing them depending on their impact to the overall mission success. In this work we present such control laws and define a number of these tasks to drive the vehicle using visual information, guarantee the robot integrity during flight, and improve the platform stability or increase arm operability. The main contributions of this research work are threefold: (1) Present a localization technique to allow autonomous navigation, this method is specifically designed for aerial platforms with size, load and computational burden restrictions. (2) Obtain control commands to drive the vehicle using visual information (visual servo). (3) Integrate the visual servo commands into a hierarchical control law by exploiting the redundancy of the robot to accomplish secondary tasks during flight. These tasks are specific for aerial manipulators and they are also provided. All the techniques presented in this document have been validated throughout extensive experimentation with real robotic platforms. i

Visual guidance fine-tunes probing movements of an insect appendage

“…Future experiments occluding the target rather than the visual field will need to establish whether hawkmoths are capable of guiding their proboscis to a target when it is temporarily occluded, thereby helping to resolve the underlying proboscis control strategy. Revealing how such a complex task can be performed with the limited computational power of an insect will be extremely instructive in revealing fundamental strategies across animals of different brain size and manipulation complexity and can serve as a bioinspiration for the growing field of aerial manipulation in robotics ( 2 , 47 ).…”

“…Visually guided reaching—to our coffee cup or a button on our phone display—is a key feature of human life ( 1 ) and increasingly frequent in robotic applications ( 2 ). It comprises an intricate neural control task, including visually identifying the target’s position in 3D space, passing the representation to the motor system, and enacting control commands to the respective appendages ( 3 – 6 ).…”

Perception in the Dark; Development of a ToF Visual Inertial Odometry System

“…In the current work, the quaternion (rotation) q, position p, velocity v, together with the biases of the gyroscope ω b and accelerometer a b are used to describe the system. Following the notation style of Santamaria-Navarro et al [26], The total system state is described by the true state p, v, ω b , a b ) and error state δx = (δθ, δp, δv, δω b , δa b ). In the error state, the Euler angles are selected to represent the rotation so that the dimension of the rotation component is 3.…”

Probabilistic Methods for Cognitive Solving of Some Problems in Artificial Intelligence Systems

“…According to this, over the decades, AI has found its application in expert systems supporting decision-making, in heuristic classification, computer vision, pattern recognition, understanding natural language, etc. [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. Here, under AI systems (AIS), we understand systems that include data processing systems that perform functions by AI, in particular by modeling and logic reasoning.…”

“…The proposed methods below do not replace existing methods for robots actions (for example, the methods of solving the systems of differential equations, the methods of refreshed linear and geometric algebra, geometry, Lie groups, linearization, solving Jacobians and Hessians, Kalman filters, Lyapunov analysis, the methods of biomechanics, graph theory, Laplas transforming for large-scale dynamic systems, etc.) [1][2][3][4][5][6][7][8][9][10][11][12][13][14].…”