Navigation through urban environments by visual perception and interaction

In this article, an admittance control strategy for aerial manipulators is proposed to achieve contact force tracking in unknown dynamic environments. First, considering the impact of variations in unknown environments on force tracking performance, an adaptive variable stiffness feature is incorporated into an advanced admittance model. The stiffness coefficient is dynamically adjusted using position and force feedback to generate the desired reference trajectory. Second, to address the issue of reference trajectory tracking under disturbances, a pose controller composed of a disturbance observer and barrier Lyapunov function is utilized to achieve stable tracking performance. In the absence of prior knowledge of disturbances, the state variables converge to a constrained range within a finite time, without introducing excessively high control gains. Finally, the stability of the proposed strategy is rigorously analyzed via Lyapunov tools. Both simulations and real-world experimental investigations are conducted to demonstrate the feasibility of the control strategy, highlighting its robust performance in maintaining a stable contact force during interaction with unknown dynamic environments.

SUMMARYWhen employing autonomous helicopters, it is desirable to use navigation approaches, which firmly ensure safety. In this paper, we propose and compare two approaches to navigation through environments containing obstacles. The first uses sliding mode boundary following to maintain a prespecified distance to obstacles, and the second uses a model predictive control approach to plan short horizon trajectories around detected objects, while ensuring that the helicopter is brought to a halt within the sensor visibility radius. The navigation approaches are subjected to analysis for robustness, and simulations are carried out with a realistic helicopter model for verification. Additional real-world experiments were performed with a wheeled robot to demonstrate potential for real-time application.

Reliance on digital navigation aids has already shown negative impacts on navigators’ innate spatial abilities. How this happens is still an open research question. We report on an empirical study with twenty-four experienced (male) taxi drivers to evaluate the long-term impacts of in-car navigation system use on the spatial learning ability of these navigation experts. Specifically, we measured cognitive load by means of electroencephalography (EEG) coupled with eye tracking to assess their visuospatial attention allocation during a video-based route-following task while driving through an unknown urban environment. We found that long-term reliance on in-car navigation aids did not affect participants’ visual attention allocation during spatial learning but rather limited their ability to encode viewed geographic information into memory, which, in turn, led to greater cognitive load, especially along route segments between intersections. Participants with greater dependence on in-car navigation aids performed worse on the spatial knowledge tests. Our combined behavioral and neuropsychological findings provide evidence for the impairment of expert navigators’ spatial learning ability when exposed to long-term use of digital in-car navigation aids.

Unmanned vehicles in urban structured environments have become the main battlefields of related companies all over the world. By relying on high-precision maps established in advance, unmanned vehicles can perform well enough. However, this method is difficult to apply to unknown off-road environment which cannot obtain high-precision maps in advance, such as transportation and target search of dangerous scenes in the wild. In this paper, we introduce a novel and efficient real-time path planning method for autonomous driving in unknown environments with sparse waypoints. The contributions of this paper are as follows. First, we present a goal point extraction algorithm to extract the goal configuration in free space for local path planning. It is extremely suitable for the sparse waypoints situation, in which local perception map may not contain any waypoints. Second, we present a novel path re-planning algorithm for large-scale environment without SLAM(Simultaneous Localization And Mapping) by building a topology map constantly. Our method not only overcame the failure of path planning due to the limited on-board sensing range, but also avoided high computing resource consumption brought by the large-scale construction maintenance of SLAM. A large number of challenging real off-road scenarios show that the proposed method can effectively solve the problem that unmanned vehicles cannot plan to travel due to sparse waypoints, and give real-time effective planning results when unmanned vehicles need to carry out large-scale path re-planning.

Enabling a flying robot to navigate autonomously in an unstructured and unknown indoor or outdoor environment is a big challenge. Attitude is one of the most important parameters for an autonomous UAV during such a flight. In this paper, we present the use of a vision system that can be used to estimate vehicle attitude using monocular pinhole camera only. Vision system are readily available on various UAV platforms and can be used for this purpose. Unlike previous work, this approach does not require (natural or artificial) parallel lines, ground markers or landmarks on the environment as clues, or use external sensors (e.g. VICON or GPS), additional on-board sensors (e.g. IMU), or additional special purpose cameras or multiple sensors. The proposed algorithm relies on on-board vision only, and the vision processing and control are performed on-board the vehicle using a single-board vision computer. After explanation of the algorithm, detailed presentation of the developed system and experimental set-up are provided. Finally, the results of the estimation and control experiments performed on a model quadrotor helicopter are presented.

This paper focuses on obstacle avoidance in the source location problem, in which robots capture the signal strength and find the signal source in an unknown environment. This work proposes a particle swarm optimizer (PSO) with a hybrid obstacle avoidance strategy to solve the problem. The signal strength is considered as the fitness function for PSO to guide robots. During moving, artificial potential fields are adopted to make robots avoid obstacles and each other. A deadlock escaping strategy is put forward to deal with the constraints of concave obstacles. The weighted average velocity of a robot is employed to check whether it is stuck by an obstacle. If so, a tabu area is set to push robots out of the area and prevent them from searching the same place again. These tabu areas offer robots key information about obstacles in an unknown environment and improve robots' ability of obstacle avoidance. The proposed algorithm is adaptive in unknown environments, meaning that no prior knowledge is needed. Simulation tests verify the effectiveness of the developed algorithm, showing satisfactory performance when dealing with concave obstacles.

Visual odometry systems are usually categorized as feature-based visual odometry systems and direct visual odometry systems. The feature-based visual odometry systems spend time on calculating descriptors while direct visual odometry systems directly calculate residuals. The optimization of direct visual odometry systems is sensitive with initial states while feature-based visual odometry systems did not suffer from this problem. This paper presents a features assisted stereo direct visual odometry system with virtual wide field-of-view tracking. It combines the advantages of feature-based methods and direct methods. It is achieved by incorporating a feature assisted predicting module and a virtual wide field-of-view tracking module into stereo direct sparse odometry (SDSO) framework. The feature-based matching is combined in direct tracking module for efficient and robust data association. Furthermore, before data association, a virtual wide field-of-view inverse depth frame is created in case of tracking lost in aggressive rotating conditions. Evaluation results on the EuRoC datasets and the KITTI dataset show that, with the aid of the new tracking module, the stereo visual odometry becomes more robust and more accurate.

Humanoid robots can imitate human behaviour and provide interactive services to humans due to their humanoid form, especially humanoid wheeled robots that can perform more complex tasks with the additional mobility. With the development of robotics technology, humanoid robots have been used increasingly in the domestic environment where the robot needs to interact with unknown environments. This requires the robot to have both the ability to track with high accuracy and the ability to comply with complex environments. It is known that the robots with impedance control can have a superior performance in terms of compliance with unknown contact environments. However, the mobility of humanoid robots with wheels complicates the dynamic model of robots, which makes the development of impedance control challenging. In this letter, a whole-body impedance control approach for humanoid wheeled robots is proposed, with fuzzy adaptive systems to compensate for the uncertain dynamics of the controlled system. This approach realizes safe interaction and compliant operation with unknown environments including humans. Additionally, the experimental results conducted on a humanoid wheeled robot illustrate the effectiveness of the proposed controller.

We address the development of the theory and algorithms that can enable a swarm of inexpensive robots or mobile sensors to create topological maps of unknown environments without explicitly requiring metric information. Topological maps are sparse and faithful representations of environments, and are useful constructions for efficient navigation in GPS-denied environments. However, in the absence of prior knowledge of the environment, with extremely limited sensing capabilities, and in an environment without localization, the construction of a topological map is a challenging problem that has not received much attention in the literature. In this letter, we present the algorithmic tools for constructing a topological map of an unknown GPS-denied environments using a swarm of resource-constrained robots. This method involves covering the free space, and then constructing an approximate generalized Voronoi graph of the covered environment. We demonstrate the algorithm using ROS, first with simulations, and then with experiments using a combination of real and virtual (simulated) robots.

This paper presents an innovative visual odometry system for fast motion estimation of autonomous space exploration vehicles. In order to improve a vehicle position recovery, the use of accelerometers and gyros is usually supported by wheels odometry. The visual system can improve the reliability of the overall rover navigation system when used in conjunction with a classical odometry system, usually affected by drift or sliding problems. The visual odometry system is based on artificial vision and reconstructs the rover position through the analysis of sequences of images acquired by two stereo cameras. The proposed algorithm is based on stereo geometry and discrete optical ow computation. From stereo geometry it is possible to locate the image points in the three dimensional environment, while from the optical ow the relative motion of the camera with respect to these points is computed. Moreover, in order to reduce the computational burden usually associated with the optical ow computation, it has been decided to first search the images for features and then to compute the discrete optical ow only associated to them. The features detection and tracking is done by using the KLT algorithm. Tests made with low resolution cameras, showing encouraging results, are presented.

Robust detection and recognition of water surfaces are critical for autonomous navigation of unmanned surface vehicles (USVs), since any none-water region is likely an obstacle posing a potential danger to the sailing vehicle. A novel water region visual detection method is proposed in this paper. First, the input image pixels are clustered into different regions and each pixel is assigned a label tag and a confidence value by adaptive multistage segmentation algorithm. Then the resulting label map and associated confidence map are fed into a convolutional neural network (CNN) as training samples to train the network online. Finally, the online trained CNN is used to segment the input image again but with greater precision and stronger robustness. Compared with other deep-learning image segmentation algorithms, the proposed method has two advantages. Firstly, it dispenses with the need of manual labeling training samples which is a costly and painful task. Secondly, it allows real-time online training for CNN, making the network adaptive to the navigational environment. Another contribution of this work relates to the training process of neuro network. An effective network training method is designed to learn from the imperfect training data. We present the experiments in the lake with a various scene and demonstrate that our proposed method could be applied to recognize the water region in the unknown navigation environment automatically.

With the continuous expansion of international terrorist organizations, terrorists have been looking for ways to cause massive destruction, in which one of dangerous weapons is a radiological source. The explosion of radiological sources makes radioactive particles scattered over a vast area, causing radiation contamination. To avoid radiation disasters, there should be autonomous mobile robots that are equipped with radiation detectors to search any radiological sources in public places. Thus, the motivation of this paper is to find out any radiological sources in an unknown environment by an autonomous mobile robot. To estimate the accurate location of a radiological source, an artificial potential field is adopted where attractive forces are modeled by a particle filter using the model of radiation sensing model. To build up an accurate sensing model, we consider the physics of radiation and the angle of incidence of gamma ray to the radiological sensor. The simulation results show that the mobile robot is able to find the radiological source in an unknown environment.

We consider the problem of team-based robot mapping and localization using wireless signals broadcast from access points embedded in today's urban environments. We map and localize in an unknown environment, where the access points' locations are unspecified and for which training data is a priori unavailable. Our approach is based on an heterogeneous method combining robots with different sensor payloads. The algorithmic design assumes the ability of producing a map in real-time from a sensor-full robot that can quickly be shared by sensor-deprived robot team members. More specifically, we cast WiFi localization as classification and regression problems that we subsequently solve using machine learning techniques. In order to produce a robust system, we take advantage of the spatial and temporal information inherent in robot motion by running Monte Carlo Localization on top of our regression algorithm, greatly improving its effectiveness. A significant amount of experiments are performed and presented to prove the accuracy, effectiveness, and practicality of the algorithm.

This paper presents a control strategy for the navigation of an autonomous vehicle through an unknown environment with a focus on real-time implementation. The task at hand is to navigate from an initial position to a predetermined goal through an unknown environment using vision as the primary sensor. To solve this problem online the system must incorporate several component technologies: estimation of the environment, dynamic path planning, and a control strategy which incorporates this information into real-time implementation. In this paper, the obstacle estimation task is performed using a combination of Structure-From-Motion (SFM) fused with inertial measurements to provide 3D information from an onboard camera and an adaptive multiresolution-based learning algorithm to estimate the environment from 3D feature points. The learned obstacle map is used as a constraint in a Receding Horizon Control (RHC) path planner which calculates dynamically feasible and locally optimal trajectories. The feasibility of the real-time implementation of this system for vehicle navigation is investigated using a Wheeled Mobile Robot (WMR) testbed with a future goal of implementation on a Micro Air Vehicle (MAV).

Robotic search often involves teleoperating vehicles into unknown environments. In such scenarios, prior knowledge of target location or environmental map may be a viable resource to tap into and control other autonomous robots in the vicinity towards an improved search performance. In this article, we test the hypothesis that despite having the same skill, prior knowledge of target or environment affects teleoperator actions, and such knowledge can therefore be inferred through robot movement. To investigate whether prior knowledge can improve human-robot team performance, we next evaluate an adaptive mutual-information blending strategy that admits a time-dependent weighting for steering autonomous robots. Human-subject experiments show that several features including distance travelled by the teleoperated robot, time spent staying still, speed, and turn rate, all depend on the level of prior knowledge and that absence of prior knowledge increased workload. Building on these results, we identified distance travelled and time spent staying still as movement cues that can be used to robustly infer prior knowledge. Simulations where an autonomous robot accompanied a human teleoperated robot revealed that whereas time to find the target was similar across all information-based search strategies, adaptive strategies that acted on movement cues found the target sooner more often than a single human teleoperator compared to non-adaptive strategies. This gain is diluted with number of robots, likely due to the limited size of the search environment. Results from this work set the stage for developing knowledge-aware control algorithms for autonomous robots in collaborative human-robot teams.