Safe Robot Trajectory Control Using Probabilistic Movement Primitives and Control Barrier Functions.

In this paper, we present a novel means of control design for probabilistic movement primitives (ProMPs). Our proposed approach makes use of control barrier functions and control Lyapunov functions defined by a ProMP distribution. Thus, a robot may move along a trajectory within the distribution while guaranteeing that the system state never leaves more than a desired distance from the distribution mean. The control employs feedback linearization to handle nonlinearities in the system dynamics and real-time quadratic programming to ensure a solution exists that satisfies all safety constraints while minimizing control effort. Furthermore, we highlight how the proposed method may allow a designer to emphasize certain safety objectives that are more important than the others. A series of simulations and experiments demonstrate the efficacy of our approach and show it can run in real time.

Heterogeneity-Aware Graph Partitioning for Distributed Deployment of Multiagent Systems.

In this work, we examine the distributed coverage control problem for deploying a team of heterogeneous robots with nonlinear dynamics in a partially known environment modeled as a weighted mixed graph. By defining an optimal tracking control problem, using a discounted cost function and state-dependent Riccati equation (SDRE) approach, a new partitioning algorithm is proposed to capture the heterogeneity in robots dynamics. The considered partitioning cost, which is a state-dependent proximity metric, penalizes both the tracking error and the control input energy that occurs during the movement of a robot, on a straight line, to an arbitrary node of the graph in a predefined finite time. We show that the size of the subgraph associated with each robot depends on its resources and capabilities in comparison to its neighbors. Also, a distributed deployment strategy is proposed to optimally distribute robots aiming at persistently monitoring specified regions of interest. Finally, a series of simulations and experimental studies is carried out to demonstrate the viability and efficacy of the proposed methodology in deploying heterogeneous multiagent systems.

Real-Time Plant Leaf Counting Using Deep Object Detection Networks.

The use of deep neural networks (DNNs) in plant phenotyping has recently received considerable attention. By using DNNs, valuable insights into plant traits can be readily achieved. While these networks have made considerable advances in plant phenotyping, the results are processed too slowly to allow for real-time decision-making. Therefore, being able to perform plant phenotyping computations in real-time has become a critical part of precision agriculture and agricultural informatics. In this work, we utilize state-of-the-art object detection networks to accurately detect, count, and localize plant leaves in real-time. Our work includes the creation of an annotated dataset of Arabidopsis plants captured using Cannon Rebel XS camera. These images and annotations have been complied and made publicly available. This dataset is then fed into a Tiny-YOLOv3 network for training. The Tiny-YOLOv3 network is then able to converge and accurately perform real-time localization and counting of the leaves. We also create a simple robotics platform based on an Android phone and iRobot create2 to demonstrate the real-time capabilities of the network in the greenhouse. Additionally, a performance comparison is conducted between Tiny-YOLOv3 and Faster R-CNN. Unlike Tiny-YOLOv3, which is a single network that does localization and identification in a single pass, the Faster R-CNN network requires two steps to do localization and identification. While with Tiny-YOLOv3, inference time, F1 Score, and false positive rate (FPR) are improved compared to Faster R-CNN, other measures such as difference in count (DiC) and AP are worsened. Specifically, for our implementation of Tiny-YOLOv3, the inference time is under 0.01 s, the F1 Score is over 0.94, and the FPR is around 24%. Last, transfer learning using Tiny-YOLOv3 to detect larger leaves on a model trained only on smaller leaves is implemented. The main contributions of the paper are in creating dataset (shared with the research community), as well as the trained Tiny-YOLOv3 network for leaf localization and counting.