This paper describes a robot system for the automatic pruning of grape vines. A mobile platform straddles the row of vines, and it images them with trinocular stereo cameras as it moves. A computer vision system builds a three-dimensional (3D) model of the vines, an artificial intelligence (AI) system decides which canes to prune, and a six degree-of-freedom robot arm makes the required cuts. The system is demonstrated cutting vines in the vineyard. The main contributions of this paper are the computer vision system that builds 3D vine models, and the test of the complete-integrated system. The vine models capture the structure of the plants so that the AI system can decide where to prune, and they are accurate enough that the robot arm can reach the required cuts. Vine models are reconstructed by matching features between images, triangulating feature matches to give a 3D model, then optimizing the model and the robot's trajectory jointly (incremental bundle adjustment). Trajectories are estimated online at 0.25 m/s, and they have errors below 1% when modeling a 96 m row of 59 vines. Pruning each vine requires the robot arm to cut an average of 8.4 canes. A collision-free trajectory for the arm is planned in intervals of 1.5 s/vine with a rapidly exploring random tree motion planner. The total time to prune one vine is 2 min in field trials, which is similar to human pruners, and it could be greatly reduced with a faster arm. Trials also show that the long chain of interdependent components limits reliability. A commercially feasible pruning robot should stop and prune each vine in turn. C 2016 Wiley Periodicals, Inc.

No abstract

Low cost MEMS sensors typically result in large position errors after very short periods of time unless they are frequently corrected by measurements from other systems. One form of measurements comes from the computer vision community where successive frames from a camera approximately looking at the ground can be used to compute the translation between frames. These measurements can be used to control the drift of an Inertial Measurement Unit (IMU) when measurements from other systems such as GPS are not available. This configuration of sensors is preferable since they are already available on some smartphones. This paper demonstrates that computer vision measurements can significantly reduce the drift of IMU-only positioning with a view for pedestrian navigation indoors. Issues such as computational requirements and operation in low light areas are also discussed.

This paper describes BoWSLAM, a scheme for a robot to reliably navigate and map previously unknown environments, in real time, using monocular vision alone. BoWSLAM can navigate challenging dynamic and self-similar environments and can recover from gross errors. Key innovations allowing this include new uses for the bag-of-words image representation; this is used to select the best set of frames from which to reconstruct positions and to give efficient wide-baseline correspondences between many pairs of frames, providing multiple position hypotheses. A graph-based representation of these position hypotheses enables the modeling and optimization of errors in scale in a dual graph and the selection of only reliable position estimates in the presence of gross outliers. BoWSLAM is demonstrated mapping a 25-min, 2.5-km trajectory through a challenging and dynamic outdoor environment without any other sensor input, considerably farther than previous single-camera simultaneous localization and mapping (SLAM) schemes. C

This paper proposes a novel solution to the problem of scale drift in single-camera simultaneous localization and mapping, based on recognizing and measuring objects. When reconstructing the trajectory of a camera moving in an unknown environment, the scale of the environment, and equivalently the speed of the camera, is obtained by accumulating relative scale estimates over sequences of frames. This leads to scale drift: errors in scale accumulate over time. The proposed solution is to learn the classes of objects that appear throughout the environment and to use measurements of the size of these objects to improve the scale estimate. A bag-of-words-based scheme to learn object classes, to recognize object instances, and to use these observations to correct scale drift is described and is demonstrated reducing accumulated errors by 64% while navigating for 2.5 km through a dynamic outdoor environment.