Obstacle Avoidance Task Research Articles

Leader–Follower Dynamics in Complex Obstacle Avoidance Task

A question that many researchers in social robotics are addressing is how to create more human-like behaviour in robots to make the collaboration between a human and a robot more intuitive to the human partner. In order to develop a human-like collaborative robotic system, however, human collaboration must first be better understood. Human collaboration is something we are all familiar with, however not that much is known about it from a kinematic standpoint. One dynamic that hasn’t been researched thoroughly, yet naturally occurs in human collaboration, is for instance leader–follower dynamics. In our previous study, we tackled the question of leader–follower role allocation in human dyads during a collaborative reaching task, where the results implied that the subjects who performed higher in the individual experiment would naturally assume the role of a leader when in physical collaboration. In this study, we build upon the leader–follower role allocation study in human dyads by observing how the leader–follower dynamics change when the collaborative task becomes more complex. Here, the study was performed on a reaching task, where one subject in a dyad was faced with an additional task of obstacle avoidance when performing a 2D reaching task, while their partner was not aware of the obstacle. We have found that subjects change their roles throughout the task in order to complete it successfully, however looking at the overall task leader the higher-performing individual will always dominate over the lower-performing one, regardless of whether they are aware of the additional task of obstacle avoidance or not.

Arm-Wrist Haptic Sleeve for Drone Teleoperation

Teleoperators rely on both visual and haptic feedback to perform drone teleoperation tasks, such as obstacle avoidance. Haptic feedback becomes essential when visual feedback is compromised, either due to visual occlusions or poor depth perception. However, haptic interfaces, are often bulky because they require heavy actuators to provide force feedback. The bulkiness reduces user mobility and makes these interfaces unsuitable for prolonged use. Here, we propose a wearable haptic sleeve that encompasses the wrist and elbow joints of a human arm. The two joint rotations control the motion of a drone in a simulated environment along a horizontal plane. The sleeve is composed of modular electroadhesive clutches that block the joint movement when the drone is in the vicinity of an obstacle. The clutches are lightweight ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$27 \,\mathrm{g}$</tex-math></inline-formula> ), require low power ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$1 \,\mathrm{m}\mathrm{W}$</tex-math></inline-formula> ) to operate, and can be mounted on the user without affecting the user’s mobility. A motor learning subject study is conducted to navigate a drone through a hole in a wall where the depth perception of visual feedback is compromised. The results of the study show that subjects trained with the wearable haptic sleeve learnt the drone obstacle avoidance task and retained the necessary motor skills after haptic training, compared to subjects who received only visual feedback and were unable to learn the motor task.

User study of sensorless adaptive haptic assistance for bilateral teleoperation

This paper presents a sensor-less haptic adaptive assistance scheme for bilateral shared controlled in telerobotics. The paper focuses on the implementation of an adaptive assistance scheme previously developed using force sensors at the master’s side, extending it to the case where this measurement is no longer available. The experimental setup was composed of a virtual slave robot and a real master robot (a commercially-of-the-shelf, low-cost haptic device), namely the Novint Falcon haptic device. Due to the lack of sensors to measure the contact force between the human operator and the haptic control device i.e., only the position of the master robot is measured, a data-driven Unknown Input Observer with disturbance estimation augmentation is proposed, allowing the estimation of the (external) human force under plant uncertainty and external disturbances. The proposed approach is tested via a path tracking (known) with (unknown) obstacle avoidance task, and statistical analysis regarding the scheme’s effectiveness is presented.

Simulation Design of a Live Working Manipulator for Patrol Inspection in Power Grid

The distribution line network is the electric power infrastructure directly facing the users, with the characteristics of large coverage and complex network, and its operation safety is directly related to the stability and reliability of the power supply system, which is the key link to ensure the safety of power supply and the reliability of residential electricity consumption. In order to realize the autonomous obstacle avoidance and autonomous navigation of the live working manipulator for inspection and maintenance of the power grid equipment, a mobile manipulator intelligent control method combining SumTree-weighted sampling and deep deterministic policy gradient (DDPG) is proposed. Firstly, the traditional DDPG algorithm is improved to optimize the action value function of Q-learning to get a better control strategy, and the weighted sampling technique is used to add priority to each sample in the replay buffer, which improves the learning speed and accelerates the convergence speed. The corresponding environmental state space is designed, and simulation experiments are conducted to verify the proposed manipulator control method. Simulation results demonstrate that the proposed method performs better than traditional DDPG and DQN methods in obstacle avoidance and navigation tasks, with faster convergence, better path planning ability, and lower offset cost, which can provide theoretical and technical references for realizing fully autonomous power grid inspection operations.

Adaptive guided salp swarm algorithm with velocity clamping mechanism for solving optimization problems

Abstract Salp swarm algorithm (SSA) is a well-established population-based optimizer that exhibits strong exploration ability, but slow convergence and poor exploitation capability. In this paper, an endeavour is made to enhance the performance of the basic SSA. The new upgraded version of SSA named as ‘adaptive strategy-based SSA (ABSSA) algorithm’ is proposed in this paper. First, the exploratory scope and food source navigating commands of SSA are enriched using the inertia weight and boosted global best-guided mechanism. Next, a novel velocity clamping strategy is designed to efficiently stabilize the balance between the exploration and exploitation operations. In addition, an adaptive conversion parameter tactic is designed to modify the position update equation to effectively intensify the local exploitation competency and solution accuracy. The effectiveness of the proposed ABSSA algorithm is verified by a series of problems, including 23 classical benchmark functions, 29 complex optimization problems from CEC 2017, and five engineering design tasks. The experimental results show that the developed ABSSA approach performs significantly better than the standard SSA and other competitors. Moreover, ABSSA is implemented to handle path planning and obstacle avoidance (PPOA) tasks in autonomous mobile robots and compared with some swarm intelligent approach-based path planners. The experimental results indicate that the ABSSA-based PPOA method is a reliable path planning algorithm.

Solution of World Robot Challenge 2020 Partner Robot Challenge (Real Space)

The World Robot Challenge is an international competition for the social implementation of robots. Among them, the Partner Robot Challenge (Real Space) is a category that focuses on domestic service robots, competing to achieve simple tasks such as tidying a room, avoiding small obstacles, grasping a specified object from the shelf, and delivering an object to a waving person. In this category, we focused on the theme of ‘Keep Moving’ and worked on researching and developing technologies for object recognition, grasping, and other tasks. For object recognition, we propose an automatic dataset generator using a physics simulator and generate about 490,000 images in two hours. We trained it with an instance segmentation model, achieving an accuracy of about 79.3% in all games. For object grasping, we installed a three-dimensional sensor on the robot hand, and achieved successful grasping with high accuracy of about 79.6% (88.9% excluding failures due to hardware problems) in all games. In addition, we propose a motion synthesis method that simultaneously performs movement and posture transition to achieve high-speed motion. When navigation is executed, the robot changes to the navigation posture while aiming for the goal. Before reaching the goal, it changes the posture for the following action. As a result, we realized a speedup of about 1.32 times in the pick-and-place task. In the tidy-up task, the robot could clear an average of 14 objects and a maximum of 16 objects in 15 minutes. In the obstacle avoidance task, the robot succeeded five times out of six games, and in the delivery task, it succeeded four times out of six games. Throughout all the tasks, we scored 800 points twice, the highest score in the world, and won the championship. This research is aimed at the practical application of domestic service robots. We believe that the results presented in this paper demonstrate the practicality of domestic service robots in a well-developed environment. The video of the finals is available at https://youtu.be/ElUb8bfSC34?t=5511 (right side). The our source code using the simulator is available at https://github.com/Hibikino-Musashi-Home/hma_wrs_sim_ws.

A Survey on Visual Simultaneously Localization and Mapping

Visual simultaneous localization and mapping (VSLAM) is an important branch of intelligent robot technology, which refers to the use of cameras as the only external sensors to achieve self-localization in unfamiliar environments while creating environmental maps. The map constructed by slam is the basis for subsequent robots to achieve autonomous positioning, path planning and obstacle avoidance tasks. This paper introduces the development of visual Slam at home and abroad, the basic methods of visual slam, and the key problems in visual slam, and discusses the main development trends and research hotspots of visual slam.

Bio-Inspired Autonomous Learning Algorithm With Application to Mobile Robot Obstacle Avoidance.

Spiking Neural Networks (SNNs) are often considered the third generation of Artificial Neural Networks (ANNs), owing to their high information processing capability and the accurate simulation of biological neural network behaviors. Though the research for SNNs has been quite active in recent years, there are still some challenges to applying SNNs to various potential applications, especially for robot control. In this study, a biologically inspired autonomous learning algorithm based on reward modulated spike-timing-dependent plasticity is proposed, where a novel rewarding generation mechanism is used to generate the reward signals for both learning and decision-making processes. The proposed learning algorithm is evaluated by a mobile robot obstacle avoidance task and experimental results show that the mobile robot with the proposed algorithm exhibits a good learning ability. The robot can successfully avoid obstacles in the environment after some learning trials. This provides an alternative method to design and apply the bio-inspired robot with autonomous learning capability in the typical robotic task scenario.

Neural network-based velocity-controllable UAV flocking

AbstractThe unmanned aerial vehicle (UAV) flocking among obstacles was transferred to a velocity-controllable UAV flocking problem, which means that multi-UAV gradually form and maintain the$\alpha$-lattice geometry as they track the desired flocking velocity, and can be applied to tasks such as obstacle avoidance and velocity tracking. Velocity-controllable UAV flocking problem is a multi-objective flocking controller parameters optimisation problem, for which we design flocking velocity and geometry objective function, and solve them using a multi-objective particle swarm optimisation algorithm (MOPSO). On this basis, to address the problem that MOPSO has random results and long computation time, we propose to use a neural network (NN) to approximate the mathematical relationship between the UAV flocking state and the flocking controller parameters. We simulate the flight process of 5 and 49 UAVs performing obstacle avoidance and velocity tracking tasks, respectively. The results show that the proposed UAV flocking controller has better convergence performance, obtains reproducible results, reduces computation time, and can be used for large-scale UAV flocking control.

Concise Discrete ZNN Controllers for End-Effector Tracking and Obstacle Avoidance of Redundant Manipulators

Obstacle avoidance is usually an additional task for a redundant manipulator when the end-effector tracking task is performed, which guarantees the safety of the redundant manipulator. By formulating and combining the end-effector tracking task and the obstacle avoidance task using zeroing neural network (ZNN), in this article, a concise continuous ZNN (CZNN) controller is first proposed. To develop discrete controllers for practical control, a second-order discrete formula and a third-order discrete formula are introduced. Therefore, by utilizing two discrete formulas to discretize the CZNN controller, two concise discrete ZNN (DZNN) controllers are proposed. Detailed theoretical analyses guarantee the effectiveness of task formulations, CZNN controller, and DZNN controllers. In addition, some comparisons with existing studies are presented in details. Furthermore, three groups of simulative experiments on the basis of UR5 manipulator and two groups of physical experiments on the basis of Kinova manipulator are conducted to illustrate the effectiveness, superiority, and practicability of two DZNN controllers.

Robotic Embodiment of Human-Like Motor Skills via Reinforcement Learning

Current methods require robots to be reprogrammed for every new task, consuming many engineering resources. This work focuses on integrating real and simulated environments for our proposed &#x201C;Internet of Skills,&#x201D; which enables robots to learn advanced skills from a small set of expert demonstrations. By expanding on recent work in the areas of Learning from Demonstrations (LfD) and Reinforcement Learning (RL), we can train robot control policies that can not only effectively complete a given task but also do so with greater performance than the expert demonstrations used to train the policy. In this work, we create simulated environments to train RL algorithms for the task of inverse kinematics and obstacle avoidance. Many state-of-the-art RL algorithms are compared, and we provide a detailed analysis of the state space and parameters chosen. Lastly, we utilize a Vicon motion tracking system and train the robot agent to follow trajectories given by a human operator. Our results show that reinforcement learning algorithms such as proximal policy optimization can develop control policies that are capable of complex control tasks that integrate with the real world, an important first step towards developing a system that can autonomously learn new skills from human demonstrations.

Advanced orthogonal opposition‐based learning‐driven dynamic salp swarm algorithm: Framework and case studies

Salp swarm algorithm (SSA) is a relatively new bio-inspired meta-heuristic optimization algorithm that mimics the navigating and foraging behavior of salps in oceans. This paper presents an orthogonal quasi-opposition-based learning-driven dynamic SSA (OBDSSA) for solving global optimization problems. The proposed methodology integrates orthogonal quasi-opposition-based learning (OQOBL) tactic and dynamic learning (DL) strategy with SSA to improve its performance. The OQOBL technique is used to enrich the exploration and development capability of the canonical SSA to help the salp chain jump out of local optimum, while the DL mechanism is applied to the basic approach to expand the neighborhood searching capabilities of the search agents. To investigate the proposed operators and OBDSSA algorithm, 18 widely used benchmark functions and parameter extraction problem of photovoltaic (PV) model have been experimented upon. The comparisons reveal that OBDSSA outperforms all competitors, including the standard SSA, SSA variants, and other state-of-the-art algorithms. Finally, the developed approach is applied to path planning and obstacle avoidance (PPOA) tasks in autonomous mobile robots (AMR) and satisfactory results are obtained.

Model-Free Safety-Critical Control for Robotic Systems

This paper presents a framework for the safety-critical control of robotic systems, when safety is defined on safe regions in the configuration space. To maintain safety, we synthesize a safe velocity based on control barrier function theory without relying on a -- potentially complicated -- high-fidelity dynamical model of the robot. Then, we track the safe velocity with a tracking controller. This culminates in model-free safety critical control. We prove theoretical safety guarantees for the proposed method. Finally, we demonstrate that this approach is application-agnostic. We execute an obstacle avoidance task with a Segway in high-fidelity simulation, as well as with a Drone and a Quadruped in hardware experiments.

Coordinated control of free-floating dual-arm space robots based on hybrid task-priority approach

This paper addresses the problem of the coordinated control of the free-floating dual-arm space robots, in the case of multiple conflict tasks. Taking the dynamic coupling effect into consideration, a relative Jacobian matrix is presented to establish the kinematic model of the free-floating dual-arm space robot. Then, an adaptive coordinated controller is elaborately developed for three conflict tasks, including position tracking of the master arm, relative motion of dual arms, and obstacle avoidance. Owing to the hybrid task-priority approach, the proposed controller can effectively ensure the execution of the obstacle avoidance task without sacrificing the performance of the first two tasks. In addition, the singularity problem is settled via introducing an adaptive damping factor based damped least-squares inverse. Meanwhile, a novel hyperbolic tangent function is designed to handle the discontinuity in performing the null space task. Finally, numerical simulations were constructed to compare the performance of the proposed coordinated controller based on hybrid task-priority approach with the controller based on task-priority approach. The simulation results show that the proposed controller has an improved tracking performance of the master arm and safety performance, compared with single task-priority approach.

Immersive Virtual Reality Simulations of Bionic Vision.

Bionic vision uses neuroprostheses to restore useful vision to people living with incurable blindness. However, a major outstanding challenge is predicting what people "see" when they use their devices. The limited field of view of current devices necessitates head movements to scan the scene, which is difficult to simulate on a computer screen. In addition, many computational models of bionic vision lack biological realism. To address these challenges, we present VR-SPV, an open-source virtual reality toolbox for simulated prosthetic vision that uses a psychophysically validated computational model to allow sighted participants to "see through the eyes" of a bionic eye user. To demonstrate its utility, we systematically evaluated how clinically reported visual distortions affect performance in a letter recognition and an immersive obstacle avoidance task. Our results highlight the importance of using an appropriate phosphene model when predicting visual outcomes for bionic vision.

Safe learning-based gradient-free model predictive control based on cross-entropy method

In this paper, a safe and learning-based control framework for model predictive control (MPC) is proposed to optimize nonlinear systems with a non-differentiable objective function under uncertain environmental disturbances. The control framework integrates a learning-based MPC with an auxiliary controller in a way of minimal intervention. The learning-based MPC augments the prior nominal model with incremental Gaussian Processes to learn the uncertain disturbances. The cross-entropy method (CEM) is utilized as the sampling-based optimizer for the MPC with a non-differentiable objective function. A minimal intervention controller is devised with a control Lyapunov function and a control barrier function to guide the sampling process and endow the system with high probabilistic safety. The proposed algorithm shows a safe and adaptive control performance on a simulated quadrotor in the tasks of trajectory tracking and obstacle avoidance under uncertain wind disturbances.

An autonomous navigation approach for unmanned vehicle in outdoor unstructured terrain with dynamic and negative obstacles

AbstractAt present, the study on autonomous unmanned ground vehicle navigation in an unstructured environment is still facing great challenges and is of great significance in scenarios where search and rescue robots, planetary exploration robots, and agricultural robots are needed. In this paper, we proposed an autonomous navigation method for unstructured environments based on terrain constraints. Efficient path search and trajectory optimization on octree map are proposed to generate trajectories, which can effectively avoid various obstacles in off-road environments, such as dynamic obstacles and negative obstacles, to reach the specified destination. We have conducted empirical experiments in both simulated and real environments, and the results show that our approach achieved superior performance in dynamic obstacle avoidance tasks and mapless navigation tasks compared to the traditional 2-dimensional or 2.5-dimensional navigation methods.

Research on Obstacle Avoidance Method of Robot Based on Region Location

In order to solve the problem of environment generalization in continuous state space, an obstacle avoidance method based on region location is proposed. The method is divided into three steps: (1) Using Region Proposal Network (RPN) to localize the obstacle area; (2). The environment map is established by the regional position mapping relation; and (3). The Deep Q-Learning Network (DQN) is used to realize collision detection of the robot, then pixel collision detection module is introduced and finally the pixel collision simulation distance sensor is combined to obtain the distance between the robot and obstacle and whether the collision or not. In this paper, the experiments were carried out in static obstacle environment and in dynamic and static obstacle environment for robot obstacle avoidance tasks. Experimental results show that the problem of environment generalization can be effectively solved by introducing pixel collision detection in the process of robot obstacle avoidance, and the network model trained in a dynamic environment has some generalization ability.

User intent estimation during robot learning using physical human robot interaction primitives

As robotic systems transition from traditional setups to collaborative work spaces, the prevalence of physical Human Robot Interaction has risen in both industrial and domestic environments. A popular representation for robot behavior is movement primitives which learn, imitate, and generalize from expert demonstrations. While there are existing works in context-aware movement primitives, they are usually limited to contact-free human robot interactions. This paper presents physical Human Robot Interaction Primitives (pHRIP), which utilize only the interaction forces between the human user and robot to estimate user intent and generate the appropriate robot response during physical human robot interactions. The efficacy of pHRIP is evaluated through multiple experiments based on target-directed reaching and obstacle avoidance tasks using a real seven degree of freedom robot arm. The results are validated against Interaction Primitives which use observations of robotic trajectories, with discussions of future pHRI applications utilizing pHRIP.

Self-perception in anorexia nervosa: When the body becomes an object

ObjectiveWomen with anorexia nervosa (AN) act as if they have a larger body, as evidenced in obstacle avoidance tasks, where an allocentric perspective is adopted. This alteration emerges not only when they perform, but also when they imagine movements. However, no previous study has investigated own body centered tasks. As such, in this study we aim at documenting if women with AN show an altered behaviour also when the task requires a first-person perspective. MethodWe explored the performance of eleven woman affected by AN compared to eighteen matched controls, in two motor imagery tasks based on a self-frame of reference, the Hand Laterality Task and the Mental Motor Chronometry Task. Moreover, two control tasks relative to visual imagery were administered. ResultsIn the Hand Laterality Task, affected participants did not adopt a motor strategy to judge hands laterality (i.e. no biomechanical constraints effect). Crucially, they also showed an altered behavior in the control task. Similarly, they did not show the expected isochrony in the Mental Motor Chronometry Task, when actions pertained the left (but not the right) hand, in absence of any difference in the control task. ConclusionsOur findings reveal altered imagery processes in AN. Specifically, affected participants adopt a third-person, rather than a first-person perspective, even when the task requires to imagine their own body in an internal frame of reference. In other words, participants with AN objectify body stimuli. Different mechanisms (i.e., checking behaviour; mirror self-reflection; altered multisensory integration) can explain such an altered imagery in AN.