Cognitive Robotics最新文献

Mobile robot path planning involves decision-making in uncertain, dynamic conditions, where Reinforcement Learning (RL) algorithms excel in generating safe and optimal paths. The Deep Deterministic Policy Gradient (DDPG) is an RL technique focused on mobile robot navigation. RL algorithms must balance exploitation and exploration to enable effective learning. The balance between these actions directly impacts learning efficiency.

This research proposes a method combining the DDPG strategy for exploitation with the Differential Gaming (DG) strategy for exploration. The DG algorithm ensures the mobile robot always reaches its target without collisions, thereby adding positive learning episodes to the memory buffer. An epsilon-greedy strategy determines whether to explore or exploit. When exploration is chosen, the DG algorithm is employed. The combination of DG strategy with DDPG facilitates faster learning by increasing the number of successful episodes and reducing the number of failure episodes in the experience buffer. The DDPG algorithm supports continuous state and action spaces, resulting in smoother, non-jerky movements and improved control over the turns when navigating obstacles. Reward shaping considers finer details, ensuring even small advantages in each iteration contribute to learning.

Through diverse test scenarios, it is demonstrated that DG exploration, compared to random exploration, results in an average increase of 389% in successful target reaches and a 39% decrease in collisions. Additionally, DG exploration shows a 69% improvement in the number of episodes where convergence is achieved within a maximum of 2000 steps.

Stroke is a leading cause of neurological disorders that result in physical disability, particularly among the elderly. Neurorehabilitation plays a crucial role in helping stroke patients recover from physical impairments and regain mobility. Physical therapy is one of the most effective forms of neurorehabilitation, but the growing number of patients requires a large workforce of trained therapists, which is currently insufficient. Robotic rehabilitation offers a promising alternative, capable of supplementing or even replacing human-assisted physical therapy through the use of rehabilitation robots. To design effective robotic devices for rehabilitation, a solid foundation of knowledge is essential. This article provides a comprehensive overview of the key elements needed to develop human upper extremity rehabilitation robots. It covers critical aspects such as upper extremity anatomy, joint range of motion, anthropometric parameters, disability assessment techniques, and robot-assisted training methods. Additionally, it reviews recent advancements in rehabilitation robots, including exoskeletons, end-effector-based robots, and planar robots. The article also evaluates existing upper extremity rehabilitation robots based on their mechanical design and functionality, identifies their limitations, and suggests future research directions for further improvement.

Path Planning in a collaborative mobile robot system has been a research topic for many years. Uncertainty in robot states, actions, and environmental conditions makes finding the optimum path for navigation highly challenging for the robot. To achieve robust behavior for mobile robots in the presence of static and dynamic obstacles, it is pertinent that the robot employs a path-finding mechanism that is based on the probabilistic perception of the uncertainty in various parameters governing its movement. Partially Observable Markov Decision Process (POMDP) is being used by many researchers as a proven methodology for handling uncertainty. The POMDP framework requires manually setting up the state transition matrix, the observation matrix, and the reward values. This paper describes an approach for creating the POMDP model and demonstrates its working by simulating it on two mobile robots destined on a collision course. Selective test cases are run on the two robots with three categories – MDP (POMDP with belief state spread of 1), POMDP with distribution spread of belief state over ten observations, and distribution spread across two observations. Uncertainty in the sensor data is simulated with varying levels of up to 10 %. The results are compared and analyzed. It is demonstrated that when the observation probability spread is increased from 2 to 10, collision reduces from 34 % to 22 %, indicating that the system's robustness increases by 12 % with only a marginal increase of 3.4 % in the computational complexity.

The motion cueing algorithm (MCA) enhances the realism of simulator driving experiences by generating vehicle motions within platform limitations. Existing MCAs are typically tuned for worst-case scenarios, limiting their efficiency for medium or slow driving motions. This study proposes a comprehensive MCA unit using learning-based models to overcome this problem and efficiently utilise the simulator workspace for all driving scenarios. Data samples are regenerated to cover various motion signal levels, and three classical washout filters are tuned to extract optimal motion signals. A multilayer perceptron (MLP) is trained with these extracted datasets, forming an AI-based MCA that provides high-fidelity driving motions for any scenario while optimising the platform workspace. Simulink/MATLAB is used for modelling and evaluation. Results demonstrate the proposed model's superior performance, with lower motion sensation errors, a higher correlation between sensed motion signals, and more efficient platform workspace usage.

Social affordances, although key in human-robot interaction processes, have received little attention in robotics. Hence, it remains unclear whether the prevailing mechanisms to exploit and learn affordances in the absence of human interaction can be extended to affordances in social contexts. This study provides a review of the concept of affordance in psychology and robotics and proposes a new view on social affordances in robotics and their differences from physical affordances. We moreover show how the model-based reinforcement learning theory provides a useful framework to study and compare social and physical affordances. To further study their differences, we present a new benchmark task mixing navigation and social interaction, in which a robot has to make a human follow and reach different goal positions in a row. This new task is solved in simulation using a modular architecture and reinforcement learning.

Unmanned Aerial Vehicles (UAVs) have become increasingly popular in recent years, with a wide range of applications in areas such as surveying, delivery, and security. UAV technology plays an important role in human life. Integrating Artificial Intelligence (AI) techniques into UAVs can significantly enhance their capabilities and performance. After the integration of AI in UAVs, their efficiency can be improved. It can automatically detect any object and highlight those objects with detailed information using AI. In most of the security surveillance places, UAV technology is beneficial. In this paper, we comprehensively reviewed the most widely used UAV communication protocols, including Wi-Fi, Zigbee, and Long-Range Wi-Fi (LoRaWAN). The review further explores valuable insights into the strengths and weaknesses of these protocols and how cognitive abilities such as perceptions and decision-making can be incorporated into UAV systems for autonomy. This paper provides a comprehensive overview of the state-of-the-art UAV object detection in remote sensing environments, as well as its types and use cases in different applications. It highlights the potential applications of these techniques in various domains, such as wildlife monitoring, search and rescue operations, and surveillance. The challenges and limitations of these methods and open research issues are given for future research.

Driving safety is significant to building a people-oriented and harmonious society, Tires are one of the key components of a vehicle and the character information on the tire sidewall is critical to their storage and usage. However, due to the diverse and differentiated features of typographic fonts, simultaneously extracting comprehensive characteristics is an extremely challenging task. To effectively break through these performance degradation issues, a multi-scale tire sidewall text region detection algorithm based on YOLOv5 is introduced, called YOLOT, which fuses comprehensive feature information in both width and depth directions. In this study, we firstly propose the Width and Depth Awareness (WDA) module in the text region detection field and successfully integrated it with the FPN structure to form the WDA-FPN. The purpose of WDA-FPN is to empower the network to capture multi-scale and multi-shape features in images, thereby augmenting the algorithm’s abstraction and representation of image features and concurrently boosting its robustness and generalization performance. Experimental findings indicate that, compared to the primary algorithm, YOLOT achieves significant improvement in accuracy, providing a higher detection reliability. The dataset and code for the paper are available at: https://github.com/Cloude-dehua/YOLOT.

Unmanned vehicles have seen a significant increase in a wide variety of fields such as for logistics, agriculture and other commercial applications. Controlling swarms of unmanned vehicles is a challenging task that requires complex autonomous control systems. Reinforcement learning has been proposed as a solution to this challenge. We propose an approach based on agent masking to enable a simple Deep Q-Network algorithm to scale on large swarms while training on relatively smaller swarms. We train our approach using multiple swarm sizes and learning rates and compare our results using metrics such as the number of collisions. We also compare the ability of our approach to scale on swarms ranging from five to 25 agents using metrics and visual analysis. Our proposed solution was able to guide a swarm of up to 100 agents to a target while keeping a good swarm cohesion and avoiding collision.

The Mobile Robot Path Problem looks to find the optimal shortest path from the starting point to the target point with collision-free for a mobile robot. This is a popular issue in robotics and in this paper the environment is considered as static and represented as a bidirectional grid map. Besides, the novel optimal method Dhouib-Matrix-SPP (DM-SPP) is applied to create the optimal shortest path for a mobile robot in a static environment. DM-SPP is a greedy method based on a column row navigation in the distance matrix and characterized by its rapidity to solve sparse graphs. The comparative analysis is conducted by applying DM-SPP on thirteen test cases and comparing its results to the results given by four metaheuristics the Max-Min Ant System, the Ant System with punitive measures, the A* and the Improved Hybrid A*. The outcomes acquired from different scenarios indicate that the proposed DM-SPP method can rapidly outperform the four predefined artificial intelligence methods.