Goal Position Research Articles

A Constraint Optimization path planning for Dynamic Environment

Optimal path planning is a major challenge for the operation of autonomous unmanned ground vehicles. In dynamic mobile path planning, the goal is to find a collision-free path for a robot from an initial position to a goal position in an environment with obstacles. However, in a dynamic environment, the challenge is bigger than static. In this paper, a modified ABC and an adaptive constraint PSO algorithm are proposed to deal with the dynamic environment; the algorithms were chosen to have a good balance between exploration and exploitation, with a penalty function used to have a collision-free path.

Simulation of Reinforcement Learning Algorithm for Motion Control of an Autonomous Humanoid

Autonomy is an issue in robotics systems. Currently the robotics research community is focusing on autonomy in the decision. The pre-programmed humanoid robots perform the operation in a known scenario. The presence of an obscure environment, a lack of awareness of the environment, humanoid robot fails to perform the random task. In such cases, the preprogrammed robot needs to be reprogrammed to enable it to perform in the changing environment. There is very limited success achieved in the autonomy of the decision-making process. This research work considered the problem of an autonomy while the deicion making in th real time interaction. The reinforcement algorithm helps to do the task in such type of unstructured and unknown environment. Reinforcement learning problems are categorized into partial Markov Decision Processes (MDP). The goal of RL agent is to minimize its immediate and expected costs. When the system interacts with the Markov Decision Process, RL agent passes through an intermediate sequence of states that depends on another by transition probabilities. The agents action takes, and the agents experience a sequence of immediate costs incurred. Reinforcement Learning and teaching approach like Queue Learning (Q-Learning) is implemented for humanoid robot for navigation and exploration. The Q-learning expresses the expected costs to go of a state action pair defined, which is meant to express the expected costs arising after having taken action in the state following policy. Based on the optimal policy of the reinforcement algorithm, a reinforcement controller was implemented. The transition probabilities of the controller depend on the randomness of the controller. The random values of the controller decide the action. Simulations were carried out for the different positions of the proposed model, and an interesting result were was observed while the transition from the sitting position to the goal position.

Efficient Deep Reinforcement Learning for Optimal Path Planning

In this paper, we propose a novel deep reinforcement learning (DRL) method for optimal path planning for mobile robots using dynamic programming (DP)-based data collection. The proposed method can overcome the slow learning process and improve training data quality inherently in DRL algorithms. The main idea of our approach is as follows. First, we mapped the dynamic programming method to typical optimal path planning problems for mobile robots, and created a new efficient DP-based method to find an exact, analytical, optimal solution for the path planning problem. Then, we used high-quality training data gathered using the DP method for DRL, which greatly improves training data quality and learning efficiency. Next, we established a two-stage reinforcement learning method where, prior to the DRL, we employed extreme learning machines (ELM) to initialize the parameters of actor and critic neural networks to a near-optimal solution in order to significantly improve the learning performance. Finally, we illustrated our method using some typical path planning tasks. The experimental results show that our DRL method can converge much easier and faster than other methods. The resulting action neural network is able to successfully guide robots from any start position in the environment to the goal position while following the optimal path and avoiding collision with obstacles.

Robotic manipulation of thin objects within off-the-shelf parallel grippers with a vibration finger

Common parallel grippers are limited to closing on an object without the ability for intrinsic in-hand manipulation. Nevertheless, parallel grippers are widely used due to their simplicity and low-cost while relying on extrinsic capabilities for manipulating the object. In this paper, a simple and low-cost mechanism is proposed for augmenting a parallel gripper with intrinsic in-hand manipulation abilities. A novel vibration-based finger was proposed where an off-the-shelf eccentric rotating mass motor along with a simple rotary actuator apply directional movement forces on a grasped thin object. The motion is based on the stick–slip phenomenon and exerted with no exposed moving parts. Along with the mechanism, a simple control law is proposed to manipulate the object to desired position goals and along paths. Furthermore, the ability to manipulate various objects is demonstrated. Experimental results show the ability to manipulate an object with accuracy of less than 2 mm. The experiments demonstrate the merits of the approach granting in-hand manipulation capabilities, that previously were not possible, to any parallel gripper. • A novel mechanism for augmenting standard parallel grippers is proposed. • The mechanism is vibration-based, low-cost and enables in-hand manipulation. • Theoretical and dynamical analysis is derived for the proposed system. • A controller is proposed to manipulate objects to goal positions and along paths. • Experimental analysis on various objects is performed.

Collision-Free Motion Algorithms for Sensors Automated Deployment to Enable a Smart Environmental Sensing-Net

As natural habitats protection has become a global priority, smart sensing-nets are ever-increasingly needed for effective environmental observation. In a practical monitoring network, it is critical to deploy sensors with sufficient automated intelligence and motion flexibility. Recent advances in robotics and sensors technology have enabled automated mobile sensors deployment in a smart sensing-net. Existing deployment algorithms can be employed to calculate adequate destinations (goals) for sensors to perform respective monitoring tasks. However, given the calculated goal positions, the problem of how to actually coordinate a fleet of robots and schedule moving paths from random initials to reach their goals safely, without collisions, remains largely unaddressed in the wireless sensor networking (WSN) literature. In this paper, we investigate this problem and propose polynomial-time collision-free motion algorithms based on batched movements to ensure all the mobile sensors reach their goals successfully without incurring collisions. We observe that the grouping (batching) strategy is similar to the coloring procedure in graph theory. By constructing a conflict graph, we model the collision-free path scheduling as the well-known k-coloring problem, from which we reduce to our k-batching problem (determining the minimum number of required batches for a successful deployment) and prove its NP completeness. Since the k-batching problem is intractable, we develop CFMA (collision-free motion algorithm), a simple yet effective batching (coloring) heuristic mechanism, to approximate the optimal solution. Performance results show that our motion algorithms outperform other existing path-scheduling mechanisms by producing 100% sensors reachability (success probability of goals reaching), time-bounded deployment latency with low computation complexity, and reduced energy consumption. Note to Practitioners— This research was originally motivated by an oceanography project, which studied marine microbes by sending a team of tiny robots (sensors) randomly scattered on the ocean floor. For hard-to-access habitats like deserts or oceans, where manual placement of sensors is costly or impossible, automatically scheduling robots movements to calculated positions from random initials is essential for an effective monitoring. Our contribution is unique in two ways. First, traditional path-planning research focuses more on independent robots navigating the environment, whereas we target on the network automation problem, coordinating a fleet of robots working together to perform an environmental sensing task. Second, we observe that existing movement methods are too complicated and energy-consuming due to the calculation on-the-go nature. To provide a practical solution, we suggest and design our motion algorithms from a new perspective: pre-scheduled batched movements. Our approach requires a central server for grouping (batching) calculations, but can effectively reduce computation complexity and save significant energy expenditure exerted on resource-limited sensors. The proposed collision-free motion algorithm (CFMA) is a suboptimal yet efficient batching solution, which can be easily applied in real-life open-space monitoring networks. Insights from this foundational research will facilitate future opportunities to implement and verify our method in operational monitoring testbeds.

A New Design Identification and Control Based on GA Optimization for An Autonomous Wheelchair

The daily lifestyle of an average human has changed drastically. Robotics and AI systems are applied to many fields, including the medical field. An autonomous wheelchair that improves the degree of independence that a wheelchair user has can be a very useful contribution to society. This paper presents the design and implementation of an autonomous wheelchair that uses LIDAR to navigate and perform SLAM. It uses the ROS framework and allows the user to choose a goal position through a touchscreen or using deep learning-based voice recognition. It also presents a practical implementation of system identification and optimization of PID control gains, which are applied to the autonomous wheelchair robot. Input/output data were collected using Arduino, consisting of linear and angular speeds and wheel PWM signal commands, and several black-box models were developed to simulate the actual wheelchair setup. The best-identified model was the NLARX model, which had the highest square error (0.1259) among the other candidate models. In addition, using MATLAB, Optimal PID gains were obtained from the genetic algorithm. Performance on real hardware was evaluated and compared to the identified model response. The two responses were identical, except for some of the noise due to the encoder measurement errors and wheelchair vibration.

Walking paths during collaborative carriages do not follow the simple rules observed in the locomotion of single walking subjects

Some works have already studied human trajectories during spontaneous locomotion. However, this topic has not been thoroughly studied in the context of human-human interactions, especially during collaborative carriage tasks. Thus, this manuscript aims to provide a broad analysis of the kinematics of two subjects carrying a table. In the present study, 20 pairs of subjects moved a table to 9 different goal positions distant of 2.7–5.4 m. This was performed with only one or both subjects knowing the target location. The analysis of the collected data demonstrated that there is no shared strategy implemented by all the pairs to move the table around. We observed a great variability in the pairs’ behaviours. Even the same pair can implement various strategies to move a table to the same goal position. Moreover, a model of the trajectories adopted by collaborating pairs was proposed and optimized with an inverse optimal control scheme. Even if it produced consistent results, due to the great variability which origins were not elucidated, it was not possible to accurately simulate the average trajectories nor the individual ones. Thus, the approach that was shown to be efficient to simulate single walking subjects failed to model the behaviour of collaborating pairs.

Navigation of Multiple Robots in Formative Manner in an Unknown Environment using Artificial Potential Field Based Path Planning Algorithm

This paper proposes a new algorithm for multiple robots that can navigate from source to goal position in a coordinated and formative manner in an optimum path and time, efficiently avoiding static and dynamic obstacles. The proposed algorithm is applied here to track surveillance for two and four robots from starting point to the goal point in an obstacle environment without collision. This algorithm is inspired by the concept of the Artificial Potential Field (APF) method and behavior-based approximate reasoning. An exhaustive search approach is used to avoid the randomly appeared obstacles, approximately estimate positions of obstacles, thus reaching the surveillance point and then tracking the allotted path for the robots. The robots are governed to move in real-time, maintaining a formation between them to track the assigned path cooperatively. The performance of this algorithm is validated in a real-time and simulation environment using MATLAB/Simulink. It is observed from the results of performance measuring parameters path length and travel time that the proposed algorithm outperforms than existing A*, RRT, and GA algorithm.

Monotonic self-stabilization and its application to robust and adaptive pattern formation

We introduce, as an enhancement of self-stabilization, the concept of monotonic self-stabilization for distributed systems that ensures that a certain measure of quality of state monotonically improves when the system in an illegitimate state progresses toward a legitimate state. In the concept, the quality is measured by a real-valued function that can be chosen from a certain class of functions. The concept is applied to a multi-robot pattern formation problem in which a group of autonomous mobile robots move from their respective initial positions to the goal positions like a marching band. We solve the problem by presenting two monotonic self-stabilizing pattern formation algorithms, one of which is for FSYNC model and the other is for SSYNC model. The considered real-valued functions to measure the quality take into account both the distance to the goal location and the accuracy of the formation. We present a formal proof of the algorithms' correctness and monotonic self-stability.

The effect of schizotypy on spatial learning in an environment with a distinctive shape.

In two experiments, participants completed the Oxford-Liverpool Inventory of Feelings and Experiences measuring schizotypal traits across four dimensions (unusual experiences, cognitive disorganization, introvertive anhedonia, and impulsive non-conformity). They then took part in a virtual navigation task where they were required to learn about the position of a hidden goal with reference to geometric cues of a rectangular arena or rely on colored wall panels to find the hidden goal in a square-shaped arena. Unusual experience and cognitive disorganization were significant predictors of the use of geometric cues, but no significant predictors were found for the use of wall panels. Implications to hippocampal function and the clinical domain are considered.

CoR-SketchAR: Cooperative Sketch-Based Real-Time Augmented Reality Authoring Tool for Crowd Simulation

In this study, we propose CoR-SketchAR, an augmented reality (AR) environment authoring tool that uses dry-erase markers for real-time collaboration among users. The most important requirement for multi-user collaboration in an AR environment is that the 3D virtual object must be placed at a specific location and can be easily changed by multiple users. Because marker-based registration techniques, which are widely used for matching virtual objects with real ones, require a marker for each object, and creating a crowd simulation environment with objects of various shapes and sizes requires the use of a large number of markers, which is time consuming and expensive. CoR-SketchAR, instead, creates an urban AR environment by drawing sketches with easily altered dry-erase marker. Then, system recognizes the shapes and colors of the sketches automatically. Those recognized shapes and colors provide the exact positions for overlaying the 3D virtual objects, which are the environment factors, on the real environment in augmented reality manner. We can even specify the path the crowd are moving along with a simple sketch stroke. We apply the computer vision technique to recognize the colors and shapes of sketches. By altering the size, shape and color sketches, the system is able to create a wide variety of dynamic urban environments. To validate the proposed techniques, we built two stand-alone software systems to check the usability of the proposed system (a 2D screen-based environmental authoring tool and a sketch-based environmental authoring tool) and conducted experiments in which two users collaborated with each other to create an environment with a specific authoring tool and then report surveys. In the experiments, users collaborated in pairs to create environmental elements, such as highways, buildings, trees, and the starting and goal positions of crowds. After recognizing them, the system then automatically creates a 3D environment, and crowds are animated accordingly. Based on a user survey, we observed that participants who used sketch-based environmental authoring tools were more active and accessible than those who used 2D screen-based authoring tools. The results of the study show that CoR-SketchAR can be further used to create a dynamical crowd simulation on a large scale using beam projectors or portable devices by simply adding sketches based on different scenarios.

Sparse Decision Diagrams for SAT-based Compilation of Multi-Agent Path Finding (Extended Abstract)

Multi-agent path finding (MAPF) represents a task of finding non-colliding paths for agents via which they can navigate from their initial positions to specified goal positions. Contemporary optimal solving algorithms include dedicated search-based methods, that solve the problem directly, and compilation-based algorithms that reduce MAPF to a different formalism for which an efficient solver exists. In this paper, we enhance the existing Boolean satisfiability-based (SAT) algorithm for MAPF via using sparse decision diagrams representing the set of candidate paths for each agent, from which the target Boolean encoding is derived, considering more promising paths before the less promising ones are taken into account. Suggested sparse diagrams lead to a smaller target Boolean formulae that can be constructed and solved faster while optimality guarantees of the approach are kept. Specifically, considering the candidate paths sparsely instead of considering them all makes the SAT-based approach more competitive for MAPF on large maps.

Leveraging Experience in Lifelong Multi-Agent Pathfinding

In Lifelong Multi-Agent Path Finding (L-MAPF) a team of agents performs a stream of tasks consisting of multiple locations to be visited by the agents on a shared graph while avoiding collisions with one another. L-MAPF is typically tackled by partitioning it into multiple consecutive, and hence similar, "one-shot" MAPF queries, as in the Rolling-Horizon Collision Resolution (RHCR) algorithm. Therefore, a solution to one query informs the next query, which leads to similarity with respect to the agents' start and goal positions, and how collisions need to be resolved from one query to the next. Thus, experience from solving one MAPF query can potentially be used to speedup solving the next one. Despite this intuition, current L-MAPF planners solve consecutive MAPF queries from scratch. In this paper, we introduce a new RHCR-inspired approach called exRHCR, which exploits experience in its constituent MAPF queries. In particular, exRHCR employs an extension of Priority-Based Search (PBS), a state-of-the-art MAPF solver. The extension, which we call exPBS, allows to warm-start the search with the priorities between agents used by PBS in the previous MAPF instances. We demonstrate empirically that exRHCR solves L-MAPF instances up to 39% faster than RHCR, and has the potential to increase system throughput for given task streams by increasing the number of agents a planner can cope with for a given time budget.

A weighted constraint satisfaction approach to human goal-directed decision making.

When we plan for long-range goals, proximal information cannot be exploited in a blindly myopic way, as relevant future information must also be considered. But when a subgoal must be resolved first, irrelevant future information should not interfere with the processing of more proximal, subgoal-relevant information. We explore the idea that decision making in both situations relies on the flexible modulation of the degree to which different pieces of information under consideration are weighted, rather than explicitly decomposing a problem into smaller parts and solving each part independently. We asked participants to find the shortest goal-reaching paths in mazes and modeled their initial path choices as a noisy, weighted information integration process. In a base task where choosing the optimal initial path required weighting starting-point and goal-proximal factors equally, participants did take both constraints into account, with participants who made more accurate choices tending to exhibit more balanced weighting. The base task was then embedded as an initial subtask in a larger maze, where the same two factors constrained the optimal path to a subgoal, and the final goal position was irrelevant to the initial path choice. In this more complex task, participants' choices reflected predominant consideration of the subgoal-relevant constraints, but also some influence of the initially-irrelevant final goal. More accurate participants placed much less weight on the optimality-irrelevant goal and again tended to weight the two initially-relevant constraints more equally. These findings suggest that humans may rely on a graded, task-sensitive weighting of multiple constraints to generate approximately optimal decision outcomes in both hierarchical and non-hierarchical goal-directed tasks.

An Optimization-Based Path Planning Approach for Autonomous Vehicles Using the DynEFWA-Artificial Potential Field

With the rapid development of autonomous driving technology, collision avoidance has become a research hotspot since it has the potential to increase safety. To obtain a collision-free path, the artificial potential field (APF) is widely used as a path planning method. APF is capable of establishing functional relationships between the vehicle and surrounding objects. However, the function features of the traditional APF method can cause autonomous vehicles to fall into the local minimum, and the generated zigzag path may be difficult to follow. Motivated by these challenges, this paper proposes a real-time path planning method for autonomous vehicles using the dynamic enhanced firework algorithm-APF. Firstly, to improve the safety and smoothness of the planned path by the traditional APF method, the constraints of the vehicle dynamics and different types of obstacles are taken into consideration. Secondly, an optimization problem is formulated to find an optimal path with the least cost in the driving area. Finally, the proposed method is verified with both a simulation and a hardware-in-loop test environment. The results show that the studied autonomous vehicle successfully avoids obstacles and arrives at the goal position by using the proposed path-planning method, and the path smoothness is improved.

Teleoperation Robot Control of a Hybrid EEG-Based BCI Arm Manipulator Using ROS

The development of assistive robots is gaining momentum in the robotic and biomedical fields. An assistive robotic system is presented in this research paper for object manipulation to aid people with physical disabilities. The robotic arm design is imported to a simulated environment and tested in a virtual world. This research includes the development of a versatile design and testing platform for robotic applications with joint torque requirements, workspace restrictions, and control tuning parameters. Live user inputs and camera feeds are used to test the movement of the robot in the virtual environment. To create the environment and user interface, a robot operating system (ROS) is used. Live brain computer interface (BCI) commands from a trained user are successfully harvested and used as an input signal to pick a goal point from 3D point cloud data and calculate the goal position of the robots’ mobile base, placing the goal point in the robot arms workspace. The platform created allows for quick design iterations to meet different application criteria and tuning of controllers for desired motion.

A Linking Invariant for Truss Robot Motion Planning

In this paper, we introduce a new invariant of C-space components for truss robots: the link-augmented graph. This invariant uses techniques from knot, link, and spatial graph theory to encode the linking information between different closed chains in the robot. For robots with a disconnected free configuration space, this invariant serves as a tool to distinguish robot configurations that lie in different connected components of C-space from each other. This can be used to eliminate goal positions that are unreachable by any collision-free motion, without needing to perform any probabilistic planning. This invariant can also be used to find appropriate assignments of node labels in a specified goal position. We demonstrate the advantages of using this invariant in conjunction with a probabilistic planner, and introduce a variant of RRT-Connect to simultaneously search for all valid goal labelings.

RRT* and Goal-Driven Variable Admittance Control for Obstacle Avoidance in Manual Guidance Applications

In manual guidance robotic applications, like the handling of large and heavy objects in a cluttered environment, it is important to guarantee that the operator accurately reaches the goal position without collisions with working isles or other obstacles in the surrounding environment. When the transported object is bulky, the operator’s view is obstructed and the situation becomes more critical. In this work, a novel variable admittance control provides the operator with a directional haptic feedback about the best motion direction towards the goal. This feedback allows the user to accurately reach the target position in a cluttered environment, also in case his/her view is partially or totally obstructed. To select the best motion direction in a cluttered workspace, a tree-based structure rooted in the goal is optimally built offline to fully explore the environment free-space based on the workspace layout and regardless of the initial position. Then, at each time instant, the optimal motion direction is determined based on the current position with respect to the exploring structure and on the user motion intention. In this work, to build the tree structure, we adapt RRT* algorithm to the manual guidance context and we define a tailored cost function. The performance is evaluated in many scenarios with a variable number of obstacles of different shapes involving several subjects and a Comau Smart Six robot.

Visual Goal Human-Robot Communication Framework With Few-Shot Learning: A Case Study in Robot Waiter System

A conventional adopted method for operating a waiter robot is based on the static position control, where predefined goal positions are marked on a map. However, this solution is not optimal in a dynamic setting, such as in a coffee shop or an outdoor catering event, because the customers often change their positions. This article explores an alternative human-robot interface design where a human operator communicates the identity of the customer to the robot instead. Inspired by how human communicates, we propose a framework for communicating a visual goal to the robot, through interactive two-way communications. The framework exploits concepts from two machine learning domains: human-in-the-loop machine learning, where active learning is used to acquire informative data, and deep metric learning, where a suitable embedding can improve the learning ability of a classifier. We also propose novel class imbalance handling techniques, which aim to actively alleviate the class imbalance problem found to be important in this mode of communication. The framework is evaluated using publicly available pedestrian datasets. We demonstrate that the proposed framework can help reduce the number of required two-way interactions and increases the robustness of the predictive model. We successfully implement the framework on a mobile robot for a delivery service in a cafe-like environment. Through the online visual goal human-robot communication, the robot can detect, recognize, and autonomously navigate to the target customer.

Multi-robot cooperation and path planning for stick transporting using improved Q-learning and democratic robotics PSO

The highlight of this paper is to propose an innovative method for solving the problem of path planning and synchronization of robot pairs in a known static and complex environment. The problem addresses the stick transportation by robot pairs from the predefined starting position to the pre-assumed goal position. This paper describes the method of computing collision-free paths for multiple numbers of paired robots called twins using a hybrid algorithm with balanced local exploitation and global exploration. The hybrid algorithm is designed by combining the individual benefits of the improved Q-Learning (IQ) and democratic robotics particle swarm optimization (DRPSO). The main intention of IQ is to produce the best position with collision avoidance by executing the best state-action pair. DRPSO algorithm computes the optimal trajectory for the twin robot using the distributed democratic approach and enhances the intensification capability. The twin robots are synchronized to the number of steps, turns, the direction of movement, and distance between both of them in the proposed approach. Computer simulation results reveal the efficacy of the proposed algorithm in both paths travelled and runtime. The experimental and VREP simulation results illustrate that the proposed algorithm offers better synchronization, cooperation, and performance in terms of several parameters such as path length, path deviation, run time, and path smoothness as a replica of the number of turns made. The comparative study with artificial bee colony optimization (ABCO) and imperialist competitive firefly algorithm (ICFA) witnesses the superiority of the hybrid IQ-DRPSO algorithm. Experiments that have been conducted through Arduino bots in a real environment prove the efficiency of the proposed approach. Results obtained from simulation and experiment reveal the supremacy of the proposed algorithm for synchronization, cooperation, and path traveled.