Bayesian iterative closest point for mobile robot localization

Accurate localization of a robot in a known environment is a fundamental capability for successfully performing path planning, manipulation, and grasping tasks. Particle filters, also known as Monte Carlo localization (MCL), are a commonly used method to determine the robot’s pose within its environment. For ground robots, noisy wheel odometry readings are typically used as a motion model to predict the vehicle’s location. Such a motion model requires tuning of various parameters based on terrain and robot type. However, such an ego-motion estimation is not always available for all platforms. Scan matching using the iterative closest point (ICP) algorithm is a popular alternative approach, providing ego-motion estimates for localization. Iterative closest point computes a point estimate of the transformation between two poses given point clouds captured at these locations. Being a point estimate method, ICP does not deal with the uncertainties in the scan alignment process, which may arise due to sensor noise, partial overlap, or the existence of multiple solutions. Another challenge for ICP is the high computational cost required to align two large point clouds, limiting its applicability to less dynamic problems. In this paper, we address these challenges by leveraging recent advances in probabilistic inference. Specifically, we first address the run-time issue and propose SGD-ICP, which employs stochastic gradient descent (SGD) to solve the optimization problem of ICP. Next, we leverage SGD-ICP to obtain a distribution over transformations and propose a Markov Chain Monte Carlo method using stochastic gradient Langevin dynamics (SGLD) updates. Our ICP variant, termed Bayesian-ICP, is a full Bayesian solution to the problem. To demonstrate the benefits of Bayesian-ICP for mobile robotic applications, we propose an adaptive motion model employing Bayesian-ICP to produce proposal distributions for Monte Carlo Localization. Experiments using both Kinect and 3D LiDAR data show that our proposed SGD-ICP method achieves the same solution quality as standard ICP while being significantly more efficient. We then demonstrate empirically that Bayesian-ICP can produce accurate distributions over pose transformations and is fast enough for online applications. Finally, using Bayesian-ICP as a motion model alleviates the need to tune the motion model parameters from odometry, resulting in better-calibrated localization uncertainty.

Multi-Sensor Fusion for Aerial Robots in Industrial GNSS-Denied Environments

The use of unmanned aerial robots has increased exponentially in recent years, and the relevance of industrial applications in environments with degraded satellite signals is rising. This article presents a solution for the 3D localization of aerial robots in such environments. In order to truly use these versatile platforms for added-value cases in these scenarios, a high level of reliability is required. Hence, the proposed solution is based on a probabilistic approach that makes use of a 3D laser scanner, radio sensors, a previously built map of the environment and input odometry, to obtain pose estimations that are computed onboard the aerial platform. Experimental results show the feasibility of the approach in terms of accuracy, robustness and computational efficiency.

An Improved Indoor Robot Human-Following Navigation Model Using Depth Camera, Active IR Marker and Proximity Sensors Fusion

Creating a navigation system for autonomous companion robots has always been a difficult process, which must contend with a dynamically changing environment, which is populated by a myriad of obstructions and an unspecific number of people, other than the intended person, to follow. This study documents the implementation of an indoor autonomous robot navigation model, based on multi-sensor fusion, using Microsoft Robotics Developer Studio 4 (MRDS). The model relies on a depth camera, a limited array of proximity sensors and an active IR marker tracking system. This allows the robot to lock onto the correct target for human-following, while approximating the best starting direction to begin maneuvering around obstacles for minimum required motion. The system is implemented according to a navigation algorithm that transforms the data from all three types of sensors into tendency arrays and fuses them to determine whether to take a leftward or rightward route around an encountered obstacle. The decision process considers visible short, medium and long-range obstructions and the current position of the target person. The system is implemented using MRDS and its functional test performance is presented over a series of Virtual Simulation Environment scenarios, greenlighting further extensive benchmark simulations.