Robot navigation is an indispensable component of any mobile service robot. Many path planning algorithms generate a path which has many sharp or angular turns. Such paths are not fit for mobile robot as it has to slow down at these sharp turns. These robots could be carrying delicate, dangerous, or precious items and executing these sharp turns may not be feasible kinematically. On the contrary, smooth trajectories are often desired for robot motion and must be generated while considering the static and dynamic obstacles and other constraints like feasible curvature, robot and lane dimensions, and speed. The aim of this paper is to succinctly summarize and review the path smoothing techniques in robot navigation and discuss the challenges and future trends. Both autonomous mobile robots and autonomous vehicles (outdoor robots or self-driving cars) are discussed. The state-of-the-art algorithms are broadly classified into different categories and each approach is introduced briefly with necessary background, merits, and drawbacks. Finally, the paper discusses the current and future challenges in optimal trajectory generation and smoothing research.

Path planning and navigation is a very important problem in robotics, especially for mobile robots operating in complex environments. Sampling based planners such as the probabilistic roadmaps (PRM) have been widely used for different robot applications. However, due to the random sampling of nodes in PRM, it suffers from narrow passage problem that generates unconnected graph. The problem is addressed by increasing the number of nodes but at higher computation cost affecting real-time performance. To address this issue, in this paper, we propose an improved sampling-based path planning method for mobile robot navigation. The proposed method uses a layered hybrid Probabilistic Roadmap (PRM) and the Artificial Potential Field (APF) method for global planning. We used a decomposition method for node distribution that uses map segmentation to produce regions of high and low potential, and propose a method of reducing the dispersion of sample set during the roadmap construction. Our method produces better goal planning queries with a smaller graph and is computationally efficient than the traditional PRM. The proposed planner called the Hybrid Potential based Probabilistic Roadmap (HPPRM) is an improved sampling method with respect to success rate and calculation cost. Furthermore, we present a method for reactive local motion planning in the presence of static and dynamic obstacles in the environment. The advantage of the proposed method is that it can avoid local minima and successfully generate plans in complex maps such as narrow passages and bug trap scenarios that are otherwise difficult for the traditional sample-based methods. We show the validity of our method with experiments in simulation and real environments for both local and global planning. The results indicate that the proposed HPPRM is effective for autonomous mobile robot navigation in complex environments. The success rate of the proposed method is higher than 95% both for local and global planning.

In past years, there has been significant progress in the field of indoor robot localization. To precisely recover the position, the robots usually relies on multiple on-board sensors. Nevertheless, this affects the overall system cost and increases computation. In this research work, we considered a light detection and ranging (LiDAR) device as the only sensor for detecting surroundings and propose an efficient indoor localization algorithm. To attenuate the computation effort and preserve localization robustness, a weighted parallel iterative closed point (WP-ICP) with interpolation is presented. As compared to the traditional ICP, the point cloud is first processed to extract corners and line features before applying point registration. Later, points labeled as corners are only matched with the corner candidates. Similarly, points labeled as lines are only matched with the lines candidates. Moreover, their ICP confidence levels are also fused in the algorithm, which make the pose estimation less sensitive to environment uncertainties. The proposed WP-ICP architecture reduces the probability of mismatch and thereby reduces the ICP iterations. Finally, based on given well-constructed indoor layouts, experiment comparisons are carried out under both clean and perturbed environments. It is shown that the proposed method is effective in significantly reducing computation effort and is simultaneously able to preserve localization precision.

In recent years, autonomous vehicle driving technology and advanced driver assistance systems have played a key role in improving road safety. However, weather conditions such as snow pose severe challenges for autonomous driving and are an active research area. Thanks to their superior reliability, the resilience of detection, and improved accuracy, advances in computation and sensor technology have paved the way for deep learning and neural network–based techniques that can replace the classical approaches. In this research, we investigate the semantic segmentation of roads in snowy environments. We propose a multi-modal fused RGB-T semantic segmentation utilizing a color (RGB) image and thermal map (T) as inputs for the network. This paper introduces a novel fusion module that combines the feature map from both inputs. We evaluate the proposed model on a new snow dataset that we collected and on other publicly available datasets. The segmentation results show that the proposed fused RGB-T input can segregate human subjects in snowy environments better than an RGB-only input. The fusion module plays a vital role in improving the efficiency of multiple input neural networks for person detection. Our results show that the proposed network can generate a higher success rate than other state-of-the-art networks. The combination of our fused module and pyramid supervision path generated the best results in both mean accuracy and mean intersection over union in every dataset.

Heterogeneous robot teams offer significant advantages for exploration and navigation missions in unknown environments. Notably, the air-ground robot teams have superior efficiency due to their mixed abilities and shared sensor resources useful when completing missions. However, the high energy consumption and reduced payload capability of the vertical take-off and landing (VTOL) aerial platforms limit the complete robot team's behavior. At some point in a mission, the aircraft needs to return to the base, land, and replenish its batteries. This task restricts the team to explore the environment in-depth and to work for longer durations. To solve this problem, we present an autonomous system for docking a VTOL-unmanned aerial vehicles (UAVs) with a mobile manipulator. The central measurement-actuation unit consists of a robot manipulator mounted on a mobile platform with a visual sensor configured as an eye-in-hand device. The visual information is used to execute a stable UAV tracking to achieve air-ground robot contact firmly. This strategy allows the multirobot team to economize and potentially recover aircraft energy. It also enables the robust ground platform to protect and store the aircraft facilitating to continue the mission for a longer duration. The on-site autonomous docking can be initiated multiple times, allowing the team to explore larger areas and complete long-term missions. The proposed method has been tested in simulations and real environments with detailed experimental results.

Line detection is an important problem in computer vision, graphics and autonomous robot navigation. Lines detected using a laser range sensor (LRS) mounted on a robot can be used as features to build a map of the environment, and later to localize the robot in the map, in a process known as Simultaneous Localization and Mapping (SLAM). We propose an efficient algorithm for line detection from LRS data using a novel hopping-points Singular Value Decomposition (SVD) and Hough transform-based algorithm, in which SVD is applied to intermittent LRS points to accelerate the algorithm. A reverse-hop mechanism ensures that the end points of the line segments are accurately extracted. Line segments extracted from the proposed algorithm are used to form a map and, subsequently, LRS data points are matched with the line segments to localize the robot. The proposed algorithm eliminates the drawbacks of point-based matching algorithms like the Iterative Closest Points (ICP) algorithm, the performance of which degrades with an increasing number of points. We tested the proposed algorithm for mapping and localization in both simulated and real environments, and found it to detect lines accurately and build maps with good self-localization.