Recent multimodal foundation models are primarily trained on English or high resource European language data, which limits their applicability to other medium and low-resource languages, such as the Indian languages. To address this limitation, we introduce Chitrarth (Chitra: Image; Artha: Meaning), an inclusive Vision-Language Model (VLM), specifically targeting the rich linguistic diversity and visual reasoning across 10 prominent Indian languages. Our model effectively integrates a state-of-the-art (SOTA) multilingual Large Language Model (LLM) with a vision module, primarily trained on multilingual image-text data. Furthermore, we also introduce BharatBench, a comprehensive framework for evaluating VLMs across various low resource languages, ultimately contributing to more diverse and effective AI systems. Our model presents SOTA results for benchmarks across Indian languages while retaining its efficiency in English. Through our research, we aim to set new benchmarks in multilingual-multimodal capabilities, offering substantial improvements over existing models and establishing a foundation for facilitating future advancements in this arena.

Addresses the kinematic modelling, solutions and trajectory planning of a tele-laparoscopic manipulator. This type of manipulator can be used in remote positioning of laparoscopic tools through a tele-operating system. Specifically the paper models kinematics of a typical manipulating system which can be used in such tele-surgery. Inverse kinematics solutions are also obtained for two kinematically constrained motions which are part of a typical trajectory of the laparoscopic tools. These are fixed axis rotation of the tool and its straight line motion. Simulation results are presented to demonstrate the validity of such models and solutions.

In endosurgery, tissue manipulation is performed by long graspers which have poor force-reflection property, i.e. they do not reflect the grasping force to the hand of the surgeon. In the paper, a novel design of an electromechanical system is considered which can enhance the force-reflecting capability of endosurgical graspers. The type synthesis of such a haptic interface leads to the application of a tunable spring. The design of the tunable spring is optimized based on the haptic and surgical requirements. Moreover, by using suitable control laws, it is shown that the primary requirements of the design application can be met. Simulation and experimental results are presented using a prototype model of such a haptic interface to demonstrate the practicality of such a design concept.

The positioning stand could help the surgeon to position and lock endoscopic tools without the need for an assistant surgeon. The kinematic configuration of the positioning stand comprises two main parts, the arm (for positioning) and the wrist (for orienting the tool). The main requirement of the wrist is to perform spherical movements around the incision point. A concentric multi-link spherical joint design has been developed for the wrist mechanism. The size synthesis is performed to minimize the overall size of wrist and also to maximize its range of angular movements. The type synthesis of the positioning arm has led to SCARA configuration, as a balanced and easy to move arm configuration. The size synthesis of the arm is carried out with the goal of minimizing its overall dimensions, based on reachable workspace and manipulability of the arm. The integration of the wrist and arm is performed by optimizing the orientation of wrist in such a way that the interference between the wrist and the workspace of surgeon is minimized.