Kowndinya Boyalakuntla

Haonan Chang, Kowndinya Boyalakuntla, Shiyang Lu et al.

We present an Open-Vocabulary 3D Scene Graph (OVSG), a formal framework for grounding a variety of entities, such as object instances, agents, and regions, with free-form text-based queries. Unlike conventional semantic-based object localization approaches, our system facilitates context-aware entity localization, allowing for queries such as ``pick up a cup on a kitchen table" or ``navigate to a sofa on which someone is sitting". In contrast to existing research on 3D scene graphs, OVSG supports free-form text input and open-vocabulary querying. Through a series of comparative experiments using the ScanNet dataset and a self-collected dataset, we demonstrate that our proposed approach significantly surpasses the performance of previous semantic-based localization techniques. Moreover, we highlight the practical application of OVSG in real-world robot navigation and manipulation experiments.

Haonan Chang, Kowndinya Boyalakuntla, Yuhan Liu et al.

Solving storage problem: where objects must be accurately placed into containers with precise orientations and positions, presents a distinct challenge that extends beyond traditional rearrangement tasks. These challenges are primarily due to the need for fine-grained 6D manipulation and the inherent multi-modality of solution spaces, where multiple viable goal configurations exist for the same storage container. We present a novel Diffusion-based Affordance Prediction (DAP) pipeline for the multi-modal object storage problem. DAP leverages a two-step approach, initially identifying a placeable region on the container and then precisely computing the relative pose between the object and that region. Existing methods either struggle with multi-modality issues or computation-intensive training. Our experiments demonstrate DAP's superior performance and training efficiency over the current state-of-the-art RPDiff, achieving remarkable results on the RPDiff benchmark. Additionally, our experiments showcase DAP's data efficiency in real-world applications, an advancement over existing simulation-driven approaches. Our contribution fills a gap in robotic manipulation research by offering a solution that is both computationally efficient and capable of handling real-world variability. Code and supplementary material can be found at: https://github.com/changhaonan/DPS.git.

Kowndinya Boyalakuntla, Akhila Sri Manasa Venigalla, Sridhar Chimalakonda

The vision of providing access to all web content equally for all users makes web accessibility a fundamental goal of today's internet. Web accessibility is the practice of removing barriers from websites that could hinder functionality for users with various disabilities. Web accessibility is measured against the accessibility guidelines such as WCAG, GIGW, and so on. WCAG 2.2 is the latest set of guidelines for web accessibility that helps in making websites accessible. The web accessibility tools available in the World Wide Web Consortium (W3C), only conform up to WCAG 2.1 guidelines, while no tools exist for the latest set of guidelines. Despite the availability of several tools to check the conformity of websites with WCAG 2.1 guidelines, there is a scarcity of tools that are both open source and scalable. To support automated accessibility evaluation of numerous websites against WCAG 2.2, 2.1, and 2.0 we present a tool, WAccess. WAccess highlights violations of 13 guidelines from WCAG 2.0, 9 guidelines from WCAG 2.1, and 7 guidelines from WCAG 2.2 of a specific web page on the web console and suggests the fix for violations while specifying violating code snippet simultaneously. We evaluated WAccess against 2227 government websites of India and observed a total of about 6.1 million violations.