Projects

[Recent Projects]

  • Motion Memory: Leveraging Past Experiences to Accelerate Future Motion Planning
    • Abstract: When facing a new motion-planning problem, most motion planners solve it from scratch, e.g., via sampling and exploration or starting optimization from a straight-line path. However, most motion planners have to experience a variety of planning problems throughout their lifetimes, which are yet to be leveraged for future planning. In this paper, we present a simple but efficient method called Motion Memory, which allows different motion planners to accelerate future planning using past experiences. Treating existing motion planners as either a closed or open box, we present a variety of ways that Motion Memory can contribute to reduce the planning time when facing a new planning problem. We provide extensive experiment results with three different motion planners on three classes of planning problems with over 30,000 problem instances and show that planning speed can be significantly reduced by up to 89% with the proposed Motion Memory technique and with increasing past planning experiences.
    • [Preprint] [Video]

[Previous Projects]

  • Reconciliation of genome assemblies from long read and short read inputs(Undergrad Thesis)
    • Abstract: Sufficient amount of de novo assemblers generate assemblies with either lesser contiguity and lesser error rate or greater contiguity and greater error rate. To maintain contiguity and accuracy at the same time, we need to take advantage from multiple assemblers, i.e. long read assemblers will ensure the contiguity and the short read assemblers will ensure accuracy. In previous studies, people put concern on employing many state-of-the-art assemblers to output an assembly which has higher accuracy. The contig integrator(CISA) is one of them, but as it chooses the contig of higher length and leave it unaltered, the error rate of the regenerated assembly remains same as the long-read-assembly, in case the multiple inputs are both long-read-assemblies and short-read-assemblies. In this manner, we modified the existing tool CISA, by providing both long-read-assembly and short-read-assembly as input and correctifying the long-read-contigs with the short-read-contigs.
  • Software Development
    • GlobeeBD: an website for ordering products online for COVID19 treatment with live covid19 data and latest COVID19 update news in Bangladesh.
    • Emblem Bangladesh: an web-based platform that incorporates Facebook profile picture of an individual to manipulate the image with his/her preferred custom filter.
    • RocketShop: an android-based application for ordering products online from a super shop.
    • Design and build backend of an online media platform.
    • Design and build a full-stack solution for online banking.