The necessity of the soft gripping devices is increasing day-by-day in medical robotics especially when safe, gentle motions and soft touch are necessary. In this paper, a novel asymmetric bellow flexible pneumatic actuator (AFPA) has been designed and fabricated to construct a miniaturised soft gripper that could be used to grip small objects. The model of AFPA is designed using solid works and its bending motion is simulated in Abaqus software for optimisation and compared with experimental results. The actuator is fabricated using compression molding process that includes micromachining of the molds. Experiments conducted show the bending characteristics of the actuator at different pressures. The actuator shows excellent bending performance and the eccentricity in its design supports increased bending or curling motion up to a certain extent compared to normal bellows without eccentricity. The effects of profile shape and eccentricity on the actuator performance are analysed and the results are presented.

Uncertainty remains a central challenge in robotic navigation, exploration, and coordination. This paper examines how Partially Observable Markov Decision Processes (POMDPs) and their decentralized variants (Dec-POMDPs) provide a rigorous foundation for decision-making under partial observability across tasks such as Active Simultaneous Localization and Mapping (A-SLAM), adaptive informative path planning, and multi-robot coordination. We review recent advances that integrate deep reinforcement learning (DRL) with POMDP formulations, highlighting improvements in scalability and adaptability as well as unresolved challenges of robustness, interpretability, and sim-to-real transfer. To complement learning-driven methods, we discuss emerging strategies that embed probabilistic reasoning directly into navigation, including belief-space planning, distributionally robust control formulations, and probabilistic graph models such as enhanced probabilistic roadmaps (PRMs) and Canadian Traveler Problem-based roadmaps. These approaches collectively demonstrate that uncertainty can be managed more effectively by coupling structured inference with data-driven adaptation. The survey concludes by outlining future research directions, emphasizing hybrid learning–planning architectures, neuro-symbolic reasoning, and socially aware navigation frameworks as critical steps toward resilient, transparent, and human-centered autonomy.

In the area of biorobotics, intense research work is being done based on plant intelligence. Any living cell continuously receives information from the environment. In this paper, research is conducted on the plant nameddescoingsiixhaworthioides(Pepe) obtaining the action potential signals and its responses to stimulations of different light modes. The plant electrical signal is the reaction of plant’s stimulation owing to various environmental conditions. Action potentials are responsible for signaling between plant cells and communication from the plants can be achieved through modulation of various parameters of the electrical signal in the plant tissue. The modulated signals are used for providing information to the microcontroller’s algorithm for working of the bio-machine. The changes of frequency of action potentials in plant are studied. Electromyography (EMG) electrodes and needle-type conductive electrodes along with electronic modules are used to collect and transform the information from the plant. Inverse fast Fourier transform (IFFT) is used to convert signal in frequency domain into voltage signal for real-time analysis. The changes in frequency of the plant action potentials to different light modes are used for the control of the bio-machine. This work has paved the way for an extensive research towards plant intelligence.