Search

Robots are now being used for maintenance, inspection, and daily activity in industrial environments such as oil and gas facilities. To perform autonomous routine inspection and maintenance, robots must be able to navigate complicated terrain, maneuvering around complex 3D obstacles and through elevation changes. ROS-based robots utilize a 2D navigation framework, leading to challenges with handling such topographically complex environments. In this thesis, a traversability mapping schema is introduced, allowing for robust mapping of environments previously unavailable to these robots. This work explores the improvements and differences between these traversable maps and the industry-standard 2D maps. The mapping setup is tested in simulation and on hardware, demonstrating an ability to quickly deploy traversability maps that allow for improved navigation of 3D terrain and avoidance of complex obstacles. Traversable maps are demonstrated to remain more than 90% consistent between separate mapping instances and accurately represent their environments to further enable complex robotic traversal.

Range-based localization is a widely used technique for position estimation where distances are measured to anchors, nodes with known positions, and the position is analytically estimated. It offers the benefits of providing high localization accuracy and involving simple operation over multiple deployments. Examples are the Global Positioning System (GPS) and network-based cellular handset localization. Range-based localization is promising for a range of applications, such as robot deployment in emergency scenarios or monitoring industrial processes. However, the presence of clutter in some of these environments leads to a severe degradation of the localization accuracy due to non-line-of-sight (NLOS) signal propagation. Moreover, current literature in NLOS-mitigation techniques requires that the NLOS distances constitute only a minority of the total number of distances to anchors. The key ideas proposed in the dissertation are: 1) multi-hop localization offers significant advantages over single-hop localization in NLOS-prone environments; and 2) it is possible to further reduce position errors by carefully placing intermediate nodes among the clutter to minimize multi-hop distances between the anchors and the unlocalized node. We demonstrate that shortest path distance (SPD) based multi-hop localization algorithms, namely DV-Distance and MDS-MAP, perform the best among other competing techniques in NLOS-prone settings. However, with random node placement, these algorithms require large node densities to produce high localization accuracy. To tackle this, we show that the strategic placement of a relatively small number of nodes in the clutter can offer significant benefits. We propose two algorithms for node placement: first, the Optimal Placement for DV-Distance (OPDV) focuses on obtaining the optimal positions of the nodes for a known clutter topology; and second, the Adaptive Placement for DV-Distance (APDV) offers a distributed control technique that carefully moves nodes in the monitored area to achieve localization accuracies close to those achieved by OPDV. We evaluate both algorithms via extensive simulations, as well as demonstrate the APDV algorithm on a real robotic hardware platform. We finally demonstrate how the characteristics of the clutter topology influence single-hop and multi-hop distance errors, which in turn, impact the performance of the proposed algorithms.

Intelligent Vehicles (IVs) present an emerging sector of automotive technology development. This study explores a specific subset of IV control logic known as path following. Complex environments, such as roadway intersections, present a significant challenge to autonomous navigation, due to the many non-standard permutations. This research sought to quantify the accuracy with which an IV could follow a set path, through a complex environment, without the aid of environmental sensors. This required the vehicle to utilize only onboard telemetry sensors to determine its relative global location in free space, and subsequently execute a move through it. The results validated the hypothesis, that an IV could follow a path, as described, with reasonable accuracy, for short distances. The vehicle navigated a 1:4.5 scale version of a complex intersection in Statesboro, GA, while maintaining effective lane tracking through four permutations of turns from the main avenue. This was accomplished by using a reverse kinematic telemetry sensor fusion approach, which leveraged the relative strengths and weaknesses of real-time processing, inertial measurement, and individual wheel speed.

One of the core competencies required for autonomous mobile robotics is the ability to use sensors to perceive the environment. From this noisy sensor data, the robot must build a representation of the environment and localize itself within this representation. This process, known as simultaneous localization and mapping (SLAM), is a prerequisite for almost all higher-level autonomous behavior in mobile robotics. By associating the robot's sensory observations as it moves through the environment, and by observing the robot's ego-motion through proprioceptive sensors, constraints are placed on the trajectory of the robot and the configuration of the environment. This results in a probabilistic optimization problem to find the most likely robot trajectory and environment configuration given all of the robot's previous sensory experience. SLAM has been well studied under the assumptions that the robot operates for a relatively short time period and that the environment is essentially static during operation. However, performing SLAM over long time periods while modeling the dynamic changes in the environment remains a challenge. The goal of this thesis is to extend the capabilities of SLAM to enable long-term autonomous operation in dynamic environments. The contribution of this thesis has three main components: First, we propose a framework for controlling the computational complexity of the SLAM optimization problem so that it does not grow unbounded with exploration time. Second, we present a method to learn visual feature descriptors that are more robust to changes in lighting, allowing for improved data association in dynamic environments. Finally, we use the proposed tools in SLAM systems that explicitly models the dynamics of the environment in the map by representing each location as a set of example views that capture how the location changes with time. We experimentally demonstrate that the proposed methods enable long-term SLAM in dynamic environments using a large, real-world vision and LIDAR dataset collected over the course of more than a year. This dataset captures a wide variety of dynamics: from short-term scene changes including moving people, cars, changing lighting, and weather conditions; to long-term dynamics including seasonal conditions and structural changes caused by construction.