Search for: All records

In this paper, we consider the problem of tracking noisy two-dimensional level curves using only the instantaneous measurements of the field, taken by two mobile agents, without the need of estimating the field gradient. To do this, we propose a dual-control-module structure consisting of the formation control and curve tracking modules. The former uses the linear velocity of the agents to generate the angular velocities, which are then used to maintain a constant distance between the two agents. The latter uses the instantaneous field measurements to generate the linear velocities of the two agents to successfully track level curves. The modular approach decouples the problems of formation control and curve tracking, thus allowing the seamless design of the two modules. We show that the proposed dual-module control structure allows fast and accurate tracking of planar level curves.

 

In this paper, a distributed cooperative filtering strategy for state estimation has been developed for mobile sensor networks in a spatial–temporal varying field modeled by the advection–diffusion equation. Sensors are organized into distributed cells that resemble a mesh grid covering a spatial area, and estimation of the field value and gradient information at each cell center is obtained by running a constrained cooperative Kalman filter while incorporating the sensor measurements and information from neighboring cells. Within each cell, the finite volume method is applied to discretize and approximate the advection–diffusion equation. These approximations build the weakly coupled relationships between neighboring cells and define the constraints that the cooperative Kalman filters are subjected to. With the estimated information, a gradient-based formation control law has been developed that enables the sensor network to adjust formation size by utilizing the estimated gradient information. Convergence analysis has been conducted for both the distributed constrained cooperative Kalman filter and the formation control. Simulation results with a 9-cell 12-sensor network validate the proposed distributed filtering method and control law. 

This paper proposes cooperative Kalman filters for distributed mobile sensor networks where the mobile sensors are organized into cells that resemble a mesh grid to cover a spatial area. The mobile sensor networks are deployed to map an underlying spatial-temporal field modeled by the Poisson equation. After discretizing the Poisson equation with finite volume method, we found that the cooperative Kalman filters for the cells are subjected to a set of distributed constraints. The field value and gradient information at each cell center can be estimated by the constrained cooperative Kalman filter using measurements within each cell and information from neighboring cells. We also provide convergence analysis for the distributed constrained cooperative Kalman filter. Simulation results with a five cell network validates the proposed distributed filtering method. 

This article presents an online parameter identification scheme for advection-diffusion processes using data collected by a mobile sensor network. The advection-diffusion equation is incorporated into the information dynamics associated with the trajectories of the mobile sensors. A constrained cooperative Kalman filter is developed to provide estimates of the field values and gradients along the trajectories of the mobile sensors so that the temporal variations in the field values can be estimated. This leads to a co-design scheme for state estimation and parameter identification for advection-diffusion processes that is different from comparable schemes using sensors installed at fixed spatial locations. Using state estimates from the constrained cooperative Kalman filter, a recursive least-square (RLS) algorithm is designed to estimate unknown model parameters of the advection-diffusion processes. Theoretical justifications are provided for the convergence of the proposed cooperative Kalman filter by deriving a set of sufficient conditions regarding the formation shape and the motion of the mobile sensor network. Simulation and experimental results show satisfactory performance and demonstrate the robustness of the algorithm under realistic uncertainties and disturbances. 

In this work, we investigate the problem of level curve tracking in unknown scalar fields using a limited number of mobile robots. We design and implement a long short-term memory (LSTM) enabled control strategy for a mobile sensor network to detect and track desired level curves. Based on the existing work of cooperative Kalman filter, we design an LSTM-enhanced Kalman filter that utilizes the sensor measurements and a sequence of past fields and gradients to estimate the current field value and gradient. We also design an LSTM model to estimate the Hessian of the field. The LSTM-enabled strategy has some benefits such as it can be trained offline on a collection of level curves in known fields prior to deployment, where the trained model will enable the mobile sensor network to track level curves in unknown fields for various applications. Another benefit is that we can train using larger resources to get more accurate models while utilizing a limited number of resources when the mobile sensor network is deployed in production. Simulation results show that this LSTM-enabled control strategy successfully tracks the level curve using a mobile multi-robot sensor network.

 

In this paper, we introduce the design and implementation of a low-cost, small-scale autonomous vehicle equipped with an onboard computer, a camera, a Lidar, and some other accessories. We implement various autonomous driving-related modules including mapping and localization, object detection, obstacle avoidance, and path planning. In order to better test the system, we focus on the autonomous parking scenario. In this scenario, the vehicle is able to move from an appointed start point to the desired parking lot autonomously by following a path planned by the hybrid A* algorithm. The vehicle is able to detect objects and avoid obstacles on its path and achieve autonomous parking. 

SUMMARY In this article, we investigate the problem of parameter identification of spatial–temporal varying processes described by a general nonlinear partial differential equation and validate the feasibility and robustness of the proposed algorithm using a group of coordinated mobile robots equipped with sensors in a realistic diffusion field. Based on the online parameter identification method developed in our previous work using multiple mobile robots, in this article, we first develop a parameterized model that represents the nonlinear spatially distributed field, then develop a parameter identification scheme consisting of a cooperative Kalman filter and recursive least square method. In the experiments, we focus on the diffusion field and consider the realistic scenarios that the diffusion field contains obstacles and hazard zones that the robots should avoid. The identified parameters together with the located source could potentially assist in the reconstruction and monitoring of the field. To validate the proposed methods, we generate a controllable carbon dioxide (CO 2 ) field in our laboratory and build a static CO 2 sensor network to measure and calibrate the field. With the reconstructed realistic diffusion field measured by the sensor network, a multi-robot system is developed to perform the parameter identification in the field. The results of simulations and experiments show satisfactory performance and robustness of the proposed algorithms. 

Recursive neural networks can be trained to serve as a memory for robots to perform intelligent behaviors when localization is not available. This paper develops an approach to convert a spatial map, represented as a scalar field, into a trained memory represented by the long short-term memory (LSTM) neural network. The trained memory can be retrieved through sensor measurements collected by robots to achieve intelligent behaviors, such as tracking level curves in the map. Memory retrieval does not require robot locations. The retrieved information is combined with sensor measurements through a Kalman filter enabled by the LSTM (LSTM-KF). Furthermore, a level curve tracking control law is designed. Simulation results show that the LSTM-KF and the control law are effective to generate level curve tracking behaviors for single-robot and multi-robot teams. 

Field coverage is a representative exploration task that has many applications ranging from household chores to navigating harsh and dangerous environments. Autonomous mobile robots are widely considered and used in such tasks due to many advantages. In particular, a collaborative multirobot group can increase the efficiency of field coverage. In this paper, we investigate the field coverage problem using a group of collaborative robots. In practical scenarios, the model of a field is usually unavailable and the robots only have access to local information obtained from their on-board sensors. Therefore, a Q-learning algorithm is developed with the joint state space being the discretized local observation areas of the robots to reduce the computational cost. We conduct simulations to verify the algorithm and compare the performance in different settings.