Hierarchical policy with deep-reinforcement learning for nonprehensile multiobject rearrangement

Bai, Fan; Meng, Fei; Liu, Jianbang; Wang, Jiankun; Meng, Max Q.-H.

doi:10.1016/j.birob.2022.100047

Cited by 6 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, multidisciplinary methods have been demonstrated to enhance knowledge gains while fostering the growth of interest, problem‐solving skills, and creative thinking. In order to merge engineering, science, and computational thinking, the Designing Biomimetic Robots action plan places a strong emphasis on problem‐based learning (CT) (Bai et al., 2022). Students study the surrounding ecosystems for 3–4 weeks to discover how animals perform various tasks, then they create a robot using what they learned as enthusiasm.…”

Section: Biomimicry‐based Strategiesmentioning

confidence: 99%

“…It will also be necessary to enhance the manipulation tool to increase the versatility and adaptability of the rearrangement process. Exhibit 10 compares the effectiveness of several success rate evaluation methods (Bai et al, 2022).…”

Section: Biomimicry‐based Strategiesmentioning

confidence: 99%

“…The search method needs to be further refined in previous stages to meet the real-time needs of the robot. It will also be necessary to enhance the manipulation tool to increase the versatility and adaptability of (Bai et al, 2022).…”

Section: Discoveries Through Biomimeticsmentioning

confidence: 99%

See 2 more Smart Citations

Biomimicry: How the environment serves as a guide for technological advancements

Thiagarajan,

Naveen,

Madhu

et al. 2023

Environmental Quality Mgmt

View full text Add to dashboard Cite

Multiple ecological tactics, like the ones described here, can be imitated to strongly affect these two components in the construction sector. This article provides an in-depth examination of the literature on biomimicry-based strategies intended to enhance building designs. This analysis is motivated by the rising need for energy legislation to achieve future local goals and provide a framework for use in Panama.These biomimicry-based methods have undergone more review and evaluation, and the incorporation of organism-based design for three of Panama's climate types has been proposed. Therefore, a SWOT analysis assisted in realizing the full potential that biomimicry-based techniques might have in raising the likelihood of satisfying local and international regulatory standards. In order to design constructions using biomimicry, multidisciplinary collaboration is required. This gives a competitive edge for better-trained human resources and expands horizons in the conventional construction industry. Finally, the analysis provided here might act as the preliminary step for the additional technical assessment using numerical and experimental procedures.

show abstract

Section: Biomimicry‐based Strategiesmentioning

confidence: 99%

Section: Biomimicry‐based Strategiesmentioning

confidence: 99%

See 1 more Smart Citation

Biomimicry: How the environment serves as a guide for technological advancements

Thiagarajan,

Naveen,

Madhu

et al. 2023

Environmental Quality Mgmt

View full text Add to dashboard Cite

show abstract

“…Model Predictive Control (MPC) combined with RL helps robots adjust their actions to deal with unexpected changes in the environment, like in legged locomotion [176,177]. Exploration methods, like Monte Carlo Tree Search (MCTS) and Proximal Policy Optimization (PPO), help robots make good decisions even in complex situations [178][179][180][181][182][183]. Hierarchical RL makes decision-making more efficient by breaking it down into smaller steps.…”

Section: Elevating Decision-making Processesmentioning

confidence: 99%

Advanced Power Converters and Learning in Diverse Robotic Innovation: A Review

Singh,

Kurukuru,

Khan

2023

Energies

View full text Add to dashboard Cite

This paper provides a comprehensive review of the integration of advanced power management systems and learning techniques in the field of robotics. It identifies the critical roles these areas play in reshaping the capabilities of robotic systems across diverse applications. To begin, it highlights the significance of efficient power usage in modern robotics. The paper explains how advanced power converters effectively control voltage, manage current and shape waveforms, thereby optimizing energy utilization. These converters ensure that robotic components receive the precise voltage levels they require, leading to improved motor performance and enabling precise control over motor behavior. Consequently, this results in extended operational times and increased design flexibility. Furthermore, the review explores the integration of learning approaches, emphasizing their substantial impact on robotic perception, decision-making and autonomy. It discusses the application of techniques such as reinforcement learning, supervised learning and unsupervised learning, showcasing their applications in areas like object recognition, semantic segmentation, sensor fusion and anomaly detection. By utilizing these learning methods, robots become more intelligent, adaptable and capable of autonomous operation across various domains. By examining the interaction between advanced power management and learning integration, this review anticipates a future where robots operate with increased efficiency, adapt to various tasks and drive technological innovation across a wide range of industries.

show abstract