Search results

This study aims to tackle control challenges in soft robots by proposing a visually-guided reinforcement learning approach. Precise tip trajectory tracking is achieved for a soft arm manipulator.

A closed-loop control strategy uses deep learning-powered perception and model-free reinforcement learning. Visual feedback detects the arm’s tip while efficient policy search is conducted via interactive sample collection.

Physical experiments demonstrate a soft arm successfully transporting objects by learning coordinated actuation policies guided by visual observations, without analytical models.

Constraints potentially include simulator gaps and dynamical variations. Future work will focus on enhancing adaptation capabilities.

By eliminating assumptions on precise analytical models or instrumentation requirements, the proposed data-driven framework offers a practical solution for real-world control challenges in soft systems.

This research provides an effective methodology integrating robust machine perception and learning for intelligent autonomous control of soft robots with complex morphologies.

This study aims to investigate and compare the influence of various fiber types (polypropylene, steel and glass) on the workability, mechanical properties, ductility, impact resistance, durability and microscopic properties of geopolymer concrete (GPC) with conventional concrete (CC).

The CC and GPC of M40 grade were incorporated with an optimum 1% of fibers and superplasticizers were added in a ratio of 2% by weight of the geopolymer binder. The slump cone and compaction factor tests were performed to analyze the workability. To evaluate the mechanical performance of GPC, the compressive strength (CS), split tensile strength (STS), flexural strength (FS) and modulus of elasticity (MOE) tests were performed. A falling weight impact test was performed to determine the impact energy (IE) absorbed, the number of blows for initial cracking, the number of blows for complete failure and the ductility aspect.

Fibers and superplasticizers significantly improve GPC properties. The study found that fibers reduce the brittleness of concrete, improving the impact and mechanical strength compared to similar-grade CC. The steel fibers-reinforced GPC has a 15.42% higher CS than CC after three days, showing a faster CS gain. After 28 days, GPC and CC have MOE in the range of 23.9–25.5 GPa and 28.8–30.9 GPa, respectively. The ultimate IE of the GPC with fibers was found to be 5.43% to 21.17% higher than GPC without fibers.

The findings of the study can be used to explore different combinations of raw materials and mix designs to optimize the performance of GPC.