Search results

This paper aims to study the agent learning from expert demonstration data while incorporating reinforcement learning (RL), which enables the agent to break through the limitations of expert demonstration data and reduces the dimensionality of the agent’s exploration space to speed up the training convergence rate.

Firstly, the decay weight function is set in the objective function of the agent’s training to combine both types of methods, and both RL and imitation learning (IL) are considered to guide the agent's behavior when updating the policy. Second, this study designs a coupling utilization method between the demonstration trajectory and the training experience, so that samples from both aspects can be combined during the agent’s learning process, and the utilization rate of the data and the agent’s learning speed can be improved.

The method is superior to other algorithms in terms of convergence speed and decision stability, avoiding training from scratch for reward values, and breaking through the restrictions brought by demonstration data.

The agent can adapt to dynamic scenes through exploration and trial-and-error mechanisms based on the experience of demonstrating trajectories. The demonstration data set used in IL and the experience samples obtained in the process of RL are coupled and used to improve the data utilization efficiency and the generalization ability of the agent.

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.

This study aims to realize efficient, fast and safe robot search task, the belief criteria decision-making approach is proposed to solve the object search task with an uncertain location.

The study formulates the robot search task as a partially observable Markov decision process, uses the semantic information to evaluate the belief state and designs the belief criteria decision-making approach. A cost function considering a trade-off among belief state, path length and movement effort is modelled to select the next best location in path planning.

The semantic information is successfully modelled and propagated, which can represent the belief of finding object. The belief criteria decision-making (BCDM) approach is evaluated in both Gazebo simulation platform and physical experiments. Compared to greedy, uniform and random methods, the performance index of path length and execution time is superior by BCDM approach.

The prior knowledge of robot working environment, especially semantic information, can be used for path planning to achieve efficient task execution in path length and execution time. The modelling and updating of environment information can lead a promising research topic to realize a more intelligent decision-making method for object search task.

Because of the various advantages of reinforcement learning (RL) mentioned above, this study uses RL to train unmanned aerial vehicles to perform two tasks: target search and cooperative obstacle avoidance.

This study draws inspiration from the recurrent state-space model and recurrent models (RPM) to propose a simpler yet highly effective model called the unmanned aerial vehicles prediction model (UAVPM). The main objective is to assist in training the UAV representation model with a recurrent neural network, using the soft actor-critic algorithm.

This study proposes a generalized actor-critic framework consisting of three modules: representation, policy and value. This architecture serves as the foundation for training UAVPM. This study proposes the UAVPM, which is designed to aid in training the recurrent representation using the transition model, reward recovery model and observation recovery model. Unlike traditional approaches reliant solely on reward signals, RPM incorporates temporal information. In addition, it allows the inclusion of extra knowledge or information from virtual training environments. This study designs UAV target search and UAV cooperative obstacle avoidance tasks. The algorithm outperforms baselines in these two environments.

It is important to note that UAVPM does not play a role in the inference phase. This means that the representation model and policy remain independent of UAVPM. Consequently, this study can introduce additional “cheating” information from virtual training environments to guide the UAV representation without concerns about its real-world existence. By leveraging historical information more effectively, this study enhances UAVs’ decision-making abilities, thus improving the performance of both tasks at hand.

Component positioning is an important part of aircraft assembly, aiming at the problem that it is difficult to accurately fall into the corresponding ball socket for the ball head connected with aircraft component. This study aims to propose a ball head adaptive positioning method based on impedance control.

First, a target impedance model for ball head positioning is constructed, and a reference positioning trajectory is generated online based on the contact force between the ball head and the ball socket. Second, the target impedance parameters were optimized based on the artificial fish swarm algorithm. Third, to improve the robustness of the impedance controller in unknown environments, a controller is designed based on model reference adaptive control (MRAC) theory and an adaptive impedance control model is built in the Simulink environment. Finally, a series of ball head positioning experiments are carried out.

During the positioning of the ball head, the contact force between the ball head and the ball socket is maintained at a low level. After the positioning, the horizontal contact force between the ball head and the socket is less than 2 N. When the position of the contact environment has the same change during ball head positioning, the contact force between the ball head and the ball socket under standard impedance control will increase to 44 N, while the contact force of the ball head and the ball socket under adaptive impedance control will only increase to 19 N.

In this paper, impedance control is used to decouple the force-position relationship of the ball head during positioning, which makes the entire process of ball head positioning complete under low stress conditions. At the same time, by constructing an adaptive impedance controller based on MRAC, the robustness of the positioning system under changes in the contact environment position is greatly improved.

Although business incubators are a widely recognized form of entrepreneurial support, this paper aims to challenge the assumption that incubation is necessarily beneficial for early-stage entrepreneurs, and considers cases where, due to variability in the motives and behaviours of entrepreneurs, incubation may be unwarranted or even undesireable.

This study presents a theoretically derived typology of incubated entrepreneurs, based on their entrepreneurial competence and capacity for learning, which asserts that incubation may be unwarranted or even undesireable for three of the four proposed entrepreneur types. Qualitative data from interviews with entrepreneurs and managing directors from 10 business incubators is used to illustrate the existence of these types.

The data provides evidence of entrepreneurial types whose incubation may be counterproductive to the goals and objectives of their host incubators.

Implications for incubator management (intake screening and ongoing monitoring of portfolio) are developed and aimed at improving the outcomes of business incubation for stakeholders.

The paper contributes to the incubation typology literature by challenging a widely held assumption that entrepreneurs have the potential to benefit from incubation and by reconceptualizing incubators as “crucibles” that perform a critical function in distinguishing high-potential entrepreneurs.

Railways are a well-known example of complex critical infrastructure, incorporating socio-technical systems with humans such as drivers, signallers, maintainers and passengers at the core. The technological evolution including interconnectedness and new ways of interaction lead to new security and safety risks that can be realised, both in terms of human error, and malicious and non-malicious behaviour. This study aims to identify the human factors (HF) and cyber-security risks relating to the role of signallers on the railways and explores strategies for the improvement of “Digital Resilience” – for the concept of a resilient railway.

Overall, 26 interviews were conducted with 21 participants from industry and academia.

The results showed that due to increased automation, both cyber-related threats and human error can impact signallers’ day-to-day operations – directly or indirectly (e.g. workload and safety-critical communications) – which could disrupt the railway services and potentially lead to safety-related catastrophic consequences. This study identifies cyber-related problems, including external threats; engineers not considering the human element in designs when specifying security controls; lack of security awareness among the rail industry; training gaps; organisational issues; and many unknown “unknowns”.

The authors discuss socio-technical principles through a hexagonal socio-technical framework and training needs analysis to mitigate against cyber-security issues and identify the predictive training needs of the signallers. This is supported by a systematic approach which considers both, safety and security factors, rather than waiting to learn from a cyber-attack retrospectively.

The author develops a bilateral Nash bargaining model under value uncertainty and private/asymmetric information, combining ideas from axiomatic and strategic bargaining theory. The solution to the model leads organically to a two-tier stochastic frontier (2TSF) setup with intra-error dependence. The author presents two different statistical specifications to estimate the model, one that accounts for regressor endogeneity using copulas, the other able to identify separately the bargaining power from the private information effects at the individual level. An empirical application using a matched employer–employee data set (MEEDS) from Zambia and a second using another one from Ghana showcase the applied potential of the approach.

This paper aims to determine the advantages and disadvantages associated with integrating a coworking environment into the real estate portfolios of large office-based organizations. The study discusses both external and internal coworking solutions.

This paper is a literature review and qualitative research based on 12 semistructured interviews with high-level real estate practitioners, including users, suppliers and consultants.

The authors examined the advantages and disadvantages of incorporating coworking environments into the real estate portfolios of large organizations from the four perspectives of Krumm et al. (2000). These perspectives were operationalized through the 12 real estate added value parameters of Jensen and Van der Voordt (2017). The findings show that improved adaptability is the greatest advantage of external coworking solutions (facility management perspective). The most significant advantage of internal coworking is related to stimulation of innovation, creativity and knowledge sharing (general management perspective). The disadvantages of external and internal coworking partly overlap and are mainly the negative effect on the corporate culture (general management perspective).

The findings contribute to the understanding of the advantages and disadvantages of incorporating both external and internal coworking solutions from multiple perspectives and allow to compare them. The authors developed and tested an operationalization of the four perspectives of Krumm (2000) through the 12 added values of Jensen and Van der Voordt (2017). Opinions and perceptions of professionals regarding internal and external coworking models are presented in a framework and related to earlier findings.

This chapter is dedicated to understanding the idea of international as a key notion to the development of globalisation and to promoting the rescaling of spaces and subjects in contemporary higher education. The author discusses the concept of scale as a performative device that activates the capacities of bodies. Instead of seeing scale as a naturalised and hierarchical structure of spatial distribution, the author understands it as an ensemble of discourses and practices that produce scalar effects. Globalisation uses scale to promote the idea that subjects would become ‘international’ by being linked to privileged spaces and bodies in the Global North. In this sense, globalisation is not merely about nodes where certain flows converge. Rather, the author understands it as the political conditions that control and constrain the space for certain flows to occur and not others. Using assemblage analysis, the author presents and analyses three scenes taken from his ethnographic records that have as a guiding line the materialisation of the international. These scenes report the experience of being a Latin American doctoral student attending a congress in the United States, a tense situation experienced at a Chilean university academic event, and the unpretentious manifestation of an elaborate idea of internationality from a personal experience of a trip to India. The results point to three elaborations of the international: an optimistic view of a shared world, a geopolitical internationality and the production of a global corporeality.