An Obstacle-crossing Strategy Based on the Fast Self-reconfiguration for Modular Sphere Robots

Luo, Haobo; Li, Ming; Liang, Guanqi; Qian, Huihuan; Lam, Tsun Ip

doi:10.1109/iros45743.2020.9341162

Cited by 11 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mechanobiology of MSCs studies the effect of mechano-niche on cell differentiation [25,26]. Previous WalkingBot [1] StarBlocks [46] ROMERIN [4] Morpho [20] Gardi et al [21] Luo et al [24] Ant3DBot [22] SMoLBot [47] This work studies [27][28][29][30] on MSCs have demonstrated the effectiveness of manual intervention [31][32][33][34][35][36] in differentiation by adjusting external loading (pressure, fluid shear, and medium stiffness), as shown in figure 1(a). Inspired by these approaches, we designed a 'differentiable' actuator and applied mechanical preloads, such as force and torque, to enable various multimodality and versatility, as shown in figure 1(b).…”

Section: Introductionmentioning

confidence: 96%

“…Bionic approaches are widely used in the design of modular robots, including footed robots [1][2][3][4][5], continuous robots [6][7][8][9][10][11][12][13][14][15][16][17], which mimic biological macrostructures, and particle robots [18][19][20][21][22][23][24]. The functionality of the modular robot depends on its configuration and size.…”

Section: Introductionmentioning

confidence: 99%

“…their configurations and capabilities are self-similar. To extend the morphology and functionality of modular robots, some research teams have been inspired by multicellular organisms to design bionic modular robots in the form of particle robots [18][19][20][21][22][23][24], enabling modules to be stacked in two and three dimensions to form robots with different morphologies. Within these robotic frameworks, although robots composed of a single kinematic module are capable of complex motions [19], the single kinematic module makes the motions of modular robots complex and overly redundant, limiting the performance of the robots as well as their potential configurations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A differentiable actuator extends potential configurations of modular robots

Li,

Zhang,

Liang

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

Mesenchymal stem cells can be differentiated into various cell lineages under the influence of mechano-niche. Inspired by this approach, this study presents a differentiable stem cell actuator unit (SAU) driven by a shape memory alloy (SMA), and a modular robotic framework. Similar to mechanically guided differentiation of mesenchymal stem cells, SAUs can be differentiated into a series of differentiated actuator units (DAUs) under external preload. This process has been modeled, simulated, and experimentally validated, with testing conducted on three distinct types and 14 specifications of DAUs. DAUs weighing as light as 1.9g exhibited outputs reaching up to 10.6N and 46.32Nmm. Our team has developed seven application prototypes based on this bio-inspired framework including mobile robots, manipulators and end effectors. This work pioneers the integration of differentiable concepts and principles into the design of modular robots, enabling a wider range of potential configurations and capabilities.

show abstract

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A differentiable actuator extends potential configurations of modular robots

Li,

Zhang,

Liang

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

show abstract

“…Remarkably, RL-based techniques have been applied to deal with the optimal configuration design problem for modular robotic arms. Luo et al proposed a self-reconfiguration algorithm based on a spherical modular robot for helping to cross various types of obstacles [4]. Whitman et al proposed a deep Q-network (DQN)-based search algorithm to solve the robot configuration synthesis problem; it is superior to existing search algorithms in terms of execution efficiency [5].…”

Section: Introductionmentioning

confidence: 99%

A Modular Robotic Arm Configuration Design Method Based on Double DQN with Prioritized Experience Replay

Ding,

Tang,

Wan

et al. 2024

Symmetry

View full text Add to dashboard Cite

The modular robotic arms can achieve desired performances in different scenarios through the combination of various modules, and concurrently hold the potential to exhibit geometric symmetry and uniform mass symmetry. Therefore, selecting the appropriate combination of modules is crucial for realizing the functions of the robotic arm and ensuring the elegance of the system. To this end, this paper proposes a double deep Q-network (DDQN)-based configuration design algorithm for modular robotic arms, which aims to find the optimal configuration under different tasks. First, a library of small modules of collaborative robotic arms consisting of multiple tandem robotic arms is constructed. These modules are described in a standard format that can be directly imported into the software for simulation, providing greater convenience and flexibility in the development of modular robotic arms. Subsequently, the DDQN design framework for module selection is established to obtain the optimal robotic arm configuration. The proposed method could deal with the overestimation problem in the traditional deep Q-network (DQN) method and improve the estimation accuracy of the value function for each module. In addition, the experience replay mechanism is improved based on the SumTree technique, which enables the algorithm to make effective use of historical experience and prevents the algorithm from falling into local optimal solutions. Finally, comparative experiments are carried out on the PyBullet simulation platform to verify the effectiveness and superiority of the configuration design method developed in the paper. The simulation results show that the proposed DDQN-based method with experience replay mechanism has higher search efficiency and accuracy compared to the traditional DQN scheme.

show abstract