Navigation Tasks Research Articles

The addition of a spatial auditory cue improves spatial updating in a virtual reality navigation task.

Auditory cues are integrated with vision and body-based self-motion cues for motion perception, balance, and gait, though limited research has evaluated their effectiveness for navigation. Here, we tested whether an auditory cue co-localized with a visual target could improve spatial updating in a virtual reality homing task. Participants navigated a triangular homing task with and without an easily localizable spatial audio signal co-located with the home location. The main outcome was unsigned angular error, defined as the absolute value of the difference between the participant's turning response and the correct response towards the home location. Angular error was significantly reduced in the presence of spatial sound compared to a head-fixed identical auditory signal. Participants' angular error was 22.79° in the presence of spatial audio and 30.09° in its absence. Those with the worst performance in the absence of spatial sound demonstrated the greatest improvement with the added sound cue. These results suggest that auditory cues may benefit navigation, particularly for those who demonstrated the highest level of spatial updating error in the absence of spatial sound.

Excessive left anterior hippocampal and caudate activation in schizophrenia underlie cognitive underperformance in a virtual navigation task

We used a virtual navigation paradigm in a city environment to assess neuroanatomical correlates of cognitive deficits in schizophrenia spectrum disorders (SSD). We studied a total of N = 36 subjects: 18 with SSD and 18 matched unaffected controls. Participants completed 10 rapid, single-trial navigation tasks within the virtual city while undergoing functional magnetic resonance imaging (fMRI). All trials tested ability to find different targets seen earlier, during the passive viewing of a path around different city blocks. SSD patients had difficulty finding previously-encountered targets, were less likely to find novel shortcuts to targets, and more likely to attempt retracing of the path observed during passive viewing. Based on a priori region-of-interest analyses, SSD participants had hyperactivation of the left hippocampus when passively viewing turns, hyperactivation of the left caudate when finding targets, and hypoactivation of a focal area of the dorsolateral prefrontal cortex when targets were initially shown during passive viewing. We propose that these brain-behaviour relations may bias or reinforce stimulus-response navigation approaches in SSD and underlie impaired performance when allocentric spatial memory is required, such as when forming efficient shortcuts. This pattern may extend to more general cognitive impairments in SSD that could be used to design remediation strategies.

Visual Servoing Architecture of Mobile Manipulators for Precise Industrial Operations on Moving Objects

Although the use of articulated robots and AGVs is common in many industrial sectors such as automotive or aeronautics, the use of mobile manipulators is not widespread nowadays. Even so, the majority of applications separate the navigation and manipulation tasks, avoiding simultaneous movements of the platform and arm. The capability to use mobile manipulators to perform operations on moving objects would open the door to new applications such as the riveting or screwing of parts transported by conveyor belts or AGVs. This paper presents a novel position-based visual servoing (PBVS) architecture for mobile manipulators for precise industrial operations on moving parts. The proposed architecture includes a state machine to guide the process through the different phases of the task to ensure its correct execution. The approach has been validated in an industrial environment for screw-fastening operations, obtaining promising results and metrics.

Representational drift as a result of implicit regularization

Recent studies show that, even in constant environments, the tuning of single neurons changes over time in a variety of brain regions. This representational drift has been suggested to be a consequence of continuous learning under noise, but its properties are still not fully understood. To investigate the underlying mechanism, we trained an artificial network on a simplified navigational task. The network quickly reached a state of high performance, and many units exhibited spatial tuning. We then continued training the network and noticed that the activity became sparser with time. Initial learning was orders of magnitude faster than ensuing sparsification. This sparsification is consistent with recent results in machine learning, in which networks slowly move within their solution space until they reach a flat area of the loss function. We analyzed four datasets from different labs, all demonstrating that CA1 neurons become sparser and more spatially informative with exposure to the same environment. We conclude that learning is divided into three overlapping phases: (i) Fast familiarity with the environment; (ii) slow implicit regularization; and (iii) a steady state of null drift. The variability in drift dynamics opens the possibility of inferring learning algorithms from observations of drift statistics.

Representational drift as a result of implicit regularization.

Recent studies show that, even in constant environments, the tuning of single neurons changes over time in a variety of brain regions. This representational drift has been suggested to be a consequence of continuous learning under noise, but its properties are still not fully understood. To investigate the underlying mechanism, we trained an artificial network on a simplified navigational task. The network quickly reached a state of high performance, and many units exhibited spatial tuning. We then continued training the network and noticed that the activity became sparser with time. Initial learning was orders of magnitude faster than ensuing sparsification. This sparsification is consistent with recent results in machine learning, in which networks slowly move within their solution space until they reach a flat area of the loss function. We analyzed four datasets from different labs, all demonstrating that CA1 neurons become sparser and more spatially informative with exposure to the same environment. We conclude that learning is divided into three overlapping phases: (i) Fast familiarity with the environment; (ii) slow implicit regularization; and (iii) a steady state of null drift. The variability in drift dynamics opens the possibility of inferring learning algorithms from observations of drift statistics.

Forming cognitive maps for abstract spaces: the roles of the human hippocampus and orbitofrontal cortex.

How does the human brain construct cognitive maps for decision-making and inference? Here, we conduct an fMRI study on a navigation task in multidimensional abstract spaces. Using a deep neural network model, we assess learning levels and categorized paths into exploration and exploitation stages. Univariate analyses show higher activation in the bilateral hippocampus and lateral prefrontal cortex during exploration, positively associated with learning level and response accuracy. Conversely, the bilateral orbitofrontal cortex (OFC) and retrosplenial cortex show higher activation during exploitation, negatively associated with learning level and response accuracy. Representational similarity analysis show that the hippocampus, entorhinal cortex, and OFC more accurately represent destinations in exploitation than exploration stages. These findings highlight the collaboration between the medial temporal lobe and prefrontal cortex in learning abstract space structures. The hippocampus may be involved in spatial memory formation and representation, while the OFC integrates sensory information for decision-making in multidimensional abstract spaces.

A data and physical model dual-driven based trajectory estimator for long-term navigation

Long-term navigation ability based on consumer-level wearable inertial sensors plays an essential role towards various emerging fields, for instance, smart healthcare, emergency rescue, soldier positioning et al. The performance of existing long-term navigation algorithm is limited by the cumulative error of inertial sensors, disturbed local magnetic field, and complex motion modes of the pedestrian. This paper develops a robust data and physical model dual-driven based trajectory estimation (DPDD-TE) framework, which can be applied for long-term navigation tasks. A Bi-directional Long Short-Term Memory (Bi-LSTM) based quasi-static magnetic field (QSMF) detection algorithm is developed for extracting useful magnetic observation for heading calibration, and another Bi-LSTM is adopted for walking speed estimation by considering hybrid human motion information under a specific time period. In addition, a data and physical model dual-driven based multi-source fusion model is proposed to integrate basic INS mechanization and multi-level constraint and observations for maintaining accuracy under long-term navigation tasks, and enhanced by the magnetic and trajectory features assisted loop detection algorithm. Real-world experiments indicate that the proposed DPDD-TE outperforms than existing algorithms, and final estimated heading and positioning accuracy indexes reaches 5° and less than 2 m under the time period of 30 min, respectively.

Research on prediction of water target motion status of unmanned surface vehicle based on lidar

To improve the perception ability of unmanned boats on water targets and improve the autonomous collision avoidance function of unmanned boats, the problem of target motion state prediction is studied and a method for predicting the motion state of unmanned water targets based on lidar is proposed. Firstly, a three-dimensional point cloud space model is established and the down-sampling and clutter filtering are completed through various filters. Secondly, based on European clustering target segmentation, a target tracking algorithm combined with 3D-IOU metric is proposed to achieve target tracking. Finally, the Kalman filter is introduced for denoising, combined with the iterative closest point algorithm (Iterative Closest Point, ICP) and the centroid calculation algorithm to realize the prediction of the target speed and course. After the test on the lake, the method can meet the real-time requirements, complete the accurate prediction of the target motion state and control the error at a low level. At the same time, this method can also lay the foundation for the development of subsequent autonomous navigation tasks of unmanned vehicles.

Autonomous Robots Traverse Multi-Terrain Environments via Hierarchical Reinforcement Learning with Skill Discovery

Although deep reinforcement learning (DRL) has been widely used in robotic mapless navigation tasks, most of the current research focuses on structured environments such as indoor or maze scenes, and little is targeted on outdoor environments. Unlike indoor environments and mazes, outdoor fields tend to be unstructured with complex landforms and sparse rewards for robotic navigation. The performance of most DRL-based strategies is directly affected by the design of the reward function, which greatly deteriorates its generalizability to outdoor environments. To this end, here we propose a two-stage learning paradigm based on skill discovery and hierarchical reinforcement learning (HRL) to cope with this challenge. Specifically, we implement skill discovery through a pre-training stage to acquire diverse skills with terrain-adaptive exploration strategies; then we select multiple skills using HRL to cope with more complex scenarios. We carry out the robotic multi-terrain traverse task based on a high-fidelity robotic simulation platform, Webots, and implement extensive comparative experiments and ablation studies to demonstrate the effectiveness of our approach.

Multi-Purpose Tracker Robot

Abstract: This paper introduces a multi-purpose tracking robot designed with Arduino, ultrasonic, infrared sensors, and motor drivers. The robot is capable of performing diverse tasks such as obstacle avoidance, line following, and object tracking. Its hardware comprises an Arduino Uno microcontroller, ultrasonic sensors for distance measurement, infrared sensors for line detection and obstacle avoidance, and motor drivers for controlling DC motors. The software, developed using Arduino IDE, includes algorithms for sensor data processing, decision-making logic, and motor control. By implementing PID control algorithms, the robot achieves enhanced stability and accuracy in navigation tasks like motor speed control and line following. Experimental results validate its effectiveness in various scenarios, showcasing its potential for advanced robotics and automation applications through intelligent sensor integration and control strategies.

Navigating the Manifold of Translucent Appearance

AbstractWe present a perceptually‐motivated manifold for translucent appearance, designed for intuitive editing of translucent materials by navigating through the manifold. Classic tools for editing translucent appearance, based on the use of sliders to tune a number of parameters, are challenging for non‐expert users: These parameters have a highly non‐linear effect on appearance, and exhibit complex interplay and similarity relations between them. Instead, we pose editing as a navigation task in a low‐dimensional space of appearances, which abstracts the user from the underlying optical parameters. To achieve this, we build a low‐dimensional continuous manifold of translucent appearance that correlates with how humans perceive this type of materials. We first analyze the correlation of different distance metrics in image space with human perception. We select the best‐performing metric to build a low‐dimensional manifold, which can be used to navigate the space of translucent appearance. To evaluate the validity of our proposed manifold within its intended application scenario, we build an editing interface that leverages the manifold, and relies on image navigation plus a fine‐tuning step to edit appearance. We compare our intuitive interface to a traditional, slider‐based one in a user study, demonstrating its effectiveness and superior performance when editing translucent objects.

Learning to Execute Timed-Temporal-Logic Navigation Tasks under Input Constraints in Obstacle-Cluttered Environments

This study focuses on addressing the problem of motion planning within workspaces cluttered with obstacles while considering temporal and input constraints. These specifications can encapsulate intricate high-level objectives involving both temporal and spatial constraints. The existing literature lacks the ability to fulfill time specifications while simultaneously managing input-saturation constraints. The proposed approach introduces a hybrid three-component control algorithm designed to learn the safe execution of a high-level specification expressed as a timed temporal logic formula across predefined regions of interest in the workspace. The first component encompasses a motion controller enabling secure navigation within the minimum allowable time interval dictated by input constraints, facilitating the abstraction of the robot’s motion as a timed transition system between regions of interest. The second component utilizes formal verification and convex optimization techniques to derive an optimal high-level timed plan over the mentioned transition system, ensuring adherence to the agent’s specification. However, the necessary navigation times and associated costs among regions are initially unknown. Consequently, the algorithm’s third component iteratively adjusts the transition system and computes new plans as the agent navigates, acquiring updated information about required time intervals and associated navigation costs. The effectiveness of the proposed scheme is demonstrated through both simulation and experimental studies.

Relation-wise transformer network and reinforcement learning for visual navigation

The task of object goal navigation is to drive an embodied agent to find the location of a given target only using visual observation. The mapping from visual perception of observation determines the navigation actions. Heterogeneous relationships in the observation are the essential part of the scene graph, which can guide the agent to find the target more easily. In this work, we propose a novel Heterogeneous Zone Graph Visual Transformer formulation for graph representation and visual perception. It consists of two key ideas: (1) Heterogeneous Zone Graph (HZG) that explores the heterogeneous target-related zones graph and spatial information. It allows the agent to navigate efficiently. (2) Relation-wise Transformer Network (RTNet) that transforms the relationship between previously observed objects and navigation actions. RTNet extracts rich nodes and edges features as pays more attention to the target-related zone. We model self-attention on the node-to-node encoder and cross-attention on the edge-to-node decoder. We evaluate our methods on the AI2THOR dataset and show superior navigation performance. Code and datasets can be found inhttps://github.com/zhoukang12321/RTNet_VN_2023.

UAV control in autonomous object-goal navigation: a systematic literature review

Research interest in autonomous control of unmanned aerial vehicles (UAVs) has increased rapidly over the past decade. They are now widely used in civilian, military, and private areas. Applications include surveillance, search and rescue, and delivery tasks. More broadly, they excel at solving problems where a significant amount of space must be covered and traveled. However, using UAVs to solve navigation problems with full autonomy necessitates the mastering of complex subtasks. A solution that includes control, planning, localization, and mapping remains an open challenge. Object-goal navigation contains the same navigation problems where the main objective is to reach a target object. The search and identification of this target are central to the vehicle’s navigation. This requires an understanding of what it is and where it can be located to move around the scene. This paper presents a systematic literature review on object-goal navigation and its subtasks, using autonomous UAVs. Survey taxonomies were found for the tasks and methods behind navigation and target localization problems using UAVs. The review analyzed 67 articles found between 2011 and 2022. They were found in the ACM, IEEE Xplore, WebOfScience, Science Direct, and Scopus databases. This review revealed essential issues related to autonomous navigation task dependencies. Moreover, it highlighted gaps in UAV development and framework standardization. Open challenges for autonomous UAV control for object-goal navigation must address the research on finding methods for problems. For example, autonomy level and comparison metrics, considering safety, ethics, and legal implications.

A hybrid connectionist/LCS for hidden-state problems

This paper describes and evaluates the performance of a learning classifier system (lcs) inspired algorithm called Temporal Reinforcement And Classification Architecture (traca) on maze navigation tasks which contain hidden state. The evaluation of traca includes comparisons with other learning algorithms on selected difficult maze navigation tasks. Not all lcss are capable of learning all types of hidden-state mazes so traca is specifically compared against selected other lcs-based approaches that are most capable on these tasks, including xcsmh, AgentP (G), and AgentP (SA). Each algorithm is evaluated using a maze navigation task that has been identified as among the most difficult due to recurring aliased regions. The comparisons between algorithms include training time, test performance, and the size of the learned rule sets. The results indicate that each algorithm has its own advantages and drawbacks. For example, on the most difficult maze traca’s average steps to the goal are 10.1 while AgentP (G) are 7.87; however, traca requires an average of only 354 training trials compared with 537 for AgentP (G). Following the maze tasks, traca is also tested on two variations in a truck driving task where it must learn to navigate four lanes of slower vehicles while avoiding collisions. The results show that traca can achieve a low number of collisions with relatively few trials (as low as 24 collisions over 5000 time steps after 10,000 training time steps) but may require multiple network construction attempts to achieve high performance.

Research on AGV scheduling and potential conflict resolution in port scenarios: based on improved genetic algorithm

In the research of Automated Guided Vehicle (AGV) scheduling, the most critical issues are the optimization of task allocation to AGVs and the handling of conflict scenarios. To address these challenges, we propose a scheme for AGV scheduling optimization and conflict resolution. To begin with, we introduce a novel improved genetic algorithm grounded on a combination strategy that re-encodes tasks into compound groupings, effectively simplifying large-scale integer programing problems into smaller, more manageable ones. Subsequently, the simplified problem is solved using an improved genetic algorithm. Test results validate that this method not only quickens the pace of finding solutions but also significantly improves the quality of those solutions. This is particularly evident when it comes to managing larger-scale optimization challenges. Furthermore, within AGV system conflict scenarios, this paper divides them into two primary categories: navigational conflicts and task quantity changes. For navigational conflicts, three resolution approaches are designed to address four different types of conflict situations: head-on, crossing, occupation, and chasing conflicts. Considering the fluctuations in task quantity, we developed strategies for rescheduling, non-rescheduling, and insertion rescheduling. Their performances were experimentally compared across various scales of scheduling problems, providing data support and theoretical basis for the selection of scheduling strategies in practical applications.

Optimizing UAV-UGV coalition operations: A hybrid clustering and multi-agent reinforcement learning approach for path planning in obstructed environment

One of the most critical applications undertaken by Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) is reaching predefined targets by following the most time-efficient routes while avoiding collisions. Unfortunately, UAVs are hampered by limited battery life, and UGVs face challenges in reachability due to obstacles and elevation variations, which is why a coalition of UAVs and UGVs can be highly effective. Existing literature primarily focuses on one-to-one coalitions, which constrains the efficiency of reaching targets. In this work, we introduce a novel approach for a UAV-UGV coalition with a variable number of vehicles, employing a modified mean-shift clustering algorithm (MEANCRFT) to segment targets into multiple zones. This approach of assigning targets to various circular zones based on density and range significantly reduces the time required to reach these targets. Moreover, introducing variability in the number of UAVs and UGVs in a coalition enhances task efficiency by enabling simultaneous multi-target engagement. In our approach, each vehicle of the coalitions is trained using two advanced deep reinforcement learning algorithms in two separate experiments, namely Multi-agent Deep Deterministic Policy Gradient (MADDPG) and Multi-agent Proximal Policy Optimization (MAPPO). The results of our experimental evaluation demonstrate that the proposed MEANCRFT-MADDPG method substantially surpasses current state-of-the-art techniques, nearly doubling efficiency in terms of target navigation time and task completion rate.

Autonomous Agent Navigation Model Based on Artificial Potential Fields Assisted by Heuristics

When autonomous agents are deployed in an unknown environment, obstacle-avoiding movement and navigation are required basic skills, all the more so when agents are limited by partial-observability constraints. This paper addresses the problem of autonomous agent navigation under partial-observability constraints by using a novel approach: Artificial Potential Fields (APF) assisted by heuristics. The well-known problem of local minima is addressed by providing the agents with the ability to make individual choices that can be exploited in a swarm. We propose a new potential function, which provides precise control of the potential field’s reach and intensity, and the use of auxiliary heuristics provides temporary target points while the agent explores, in search of the position of the real intended target. Artificial Potential Fields, together with auxiliary search heuristics, are integrated into a novel navigation model for autonomous agents who have limited or no knowledge of their environment. Experimental results are shown in 2D scenarios that pose challenging situations with multiple obstacles, local minima conditions and partial-observability constraints, clearly showing that an agent driven using the proposed model is capable of completing the navigation task, even under the partial-observability constraints.

Visuospatial Performance on Spatial Navigation Task and DASB PET Correlates in Isolated REM Sleep Behavior Disorder (P8-9.011)

Visuospatial Performance on Spatial Navigation Task and DASB PET Correlates in Isolated REM Sleep Behavior Disorder (P8-9.011)

A bio-inspired model for robust navigation assistive devices

This paper proposes a new implementation and evaluation in a real-world environment of a bio-inspired predictive navigation model for mobility control, suitable especially for assistance of visually impaired people and autonomous mobile systems. This bio-inspired model relies on the interactions between formal models of three types of neurons identified in the mammals’ brain implied in navigation tasks, namely place cells, grid cells, and head direction cells, to construct a topological model of the environment under the form of a decentralized navigation graph. Previously tested in virtual environments, this model demonstrated a high tolerance to motion drift, making possible to map large environments without the need to correct it to handle such drifts, and robustness to environment changes. The presented implementation is based on a stereoscopic camera, and is evaluated on its possibilities to map and guide a person or an autonomous mobile robot in an unknown real environment. The evaluation results confirm the effectiveness of the proposed bio-inspired navigation model to build a path map, localize and guide a person through this path. The model predictions remain robust to environment changes, and allow to estimate traveled distances with an error rate below 3% over test paths, up to 100m. The tests performed on a robotic platform also demonstrated the pertinence of navigation data produced by this navigation model to guide an autonomous system. These results open the way toward efficient wearable assistive devices for visually impaired people independent navigation.