arXiv subjects

Ashutosh Saxena

Publications and source records attributed to Ashutosh Saxena.

45 records · Page 3Linked to original sources

arXiv2011

Inferring 3D Articulated Models for Box Packaging Robot

Given a point cloud, we consider inferring kinematic models of 3D articulated objects such as boxes for the purpose of manipulating them. While previous work has shown how to extract a planar kinematic model (often represented as a linear chain), such planar models do not apply to 3D objects that are composed of segments often linked to the other segments in cyclic configurations. We present an approach for building a model that captures the relation between the input point cloud features and the object segment as well as the relation between the neighboring object segments. We use a conditional random field that allows us to model the dependencies between different segments of the object. We test our approach on inferring the kinematic structure from partial and noisy point cloud data for a wide variety of boxes including cake boxes, pizza boxes, and cardboard cartons of several sizes. The inferred structure enables our robot to successfully close these boxes by manipulating the flaps.

cs.RO↗

arXiv2011

Learning to Place New Objects

The ability to place objects in the environment is an important skill for a personal robot. An object should not only be placed stably, but should also be placed in its preferred location/orientation. For instance, a plate is preferred to be inserted vertically into the slot of a dish-rack as compared to be placed horizontally in it. Unstructured environments such as homes have a large variety of object types as well as of placing areas. Therefore our algorithms should be able to handle placing new object types and new placing areas. These reasons make placing a challenging manipulation task. In this work, we propose a supervised learning algorithm for finding good placements given the point-clouds of the object and the placing area. It learns to combine the features that capture support, stability and preferred placements using a shared sparsity structure in the parameters. Even when neither the object nor the placing area is seen previously in the training set, our algorithm predicts good placements. In extensive experiments, our method enables the robot to stably place several new objects in several new placing areas with 98% success-rate; and it placed the objects in their preferred placements in 92% of the cases.

cs.RO↗

arXiv2010

Personalized Data Set for Analysis

Data Management portfolio within an organization has seen an upsurge in initiatives for compliance, security, repurposing and storage within and outside the organization. When such initiatives are being put to practice care must be taken while granting access to data repositories for analysis and mining activities. Also, initiatives such as Master Data Management, cloud computing and self service business intelligence have raised concerns in the arena of regulatory compliance and data privacy, especially when a large data set of an organization are being outsourced for testing, consolidation and data management. Here, an approach is presented where a new service layer is introduced, by data governance group, in the architecture for data management and can be used for preserving privacy of sensitive information.

cs.DB↗

arXiv2010

MDPs with Unawareness

Markov decision processes (MDPs) are widely used for modeling decision-making problems in robotics, automated control, and economics. Traditional MDPs assume that the decision maker (DM) knows all states and actions. However, this may not be true in many situations of interest. We define a new framework, MDPs with unawareness (MDPUs) to deal with the possibilities that a DM may not be aware of all possible actions. We provide a complete characterization of when a DM can learn to play near-optimally in an MDPU, and give an algorithm that learns to play near-optimally when it is possible to do so, as efficiently as possible. In particular, we characterize when a near-optimal solution can be found in polynomial time.

cs.AI↗

arXiv2007

Proxy Signature Scheme with Effective Revocation Using Bilinear Pairings

We present a proxy signature scheme using bilinear pairings that provides effective proxy revocation. The scheme uses a binding-blinding technique to avoid secure channel requirements in the key issuance stage. With this technique, the signer receives a partial private key from a trusted authority and unblinds it to get his private key, in turn, overcomes the key escrow problem which is a constraint in most of the pairing-based proxy signature schemes. The scheme fulfills the necessary security requirements of proxy signature and resists other possible threats.

cs.CR↗

arXiv2007

A Dynamic ID-based Remote User Authentication Scheme

Password-based authentication schemes are the most widely used techniques for remote user authentication. Many static ID-based remote user authentication schemes both with and without smart cards have been proposed. Most of the schemes do not allow the users to choose and change their passwords, and maintain a verifier table to verify the validity of the user login. In this paper we present a dynamic ID-based remote user authentication scheme using smart cards. Our scheme allows the users to choose and change their passwords freely, and do not maintain any verifier table. The scheme is secure against ID-theft, and can resist the reply attacks, forgery attacks, guessing attacks, insider attacks and stolen verifier attacks.

cs.CR↗

arXiv2006

Algorithms and Approaches of Proxy Signature: A Survey

Numerous research studies have been investigated on proxy signatures over the last decade. This survey reviews the research progress on proxy signatures, analyzes a few notable proposals, and provides an overall remark of these proposals.

cs.CR↗

arXiv2005

Cryptanalysis of Key Issuing Protocols in ID-based Cryptosystems

To remove key escrow problem and avoid the need of secure channel in ID based cryptosystem Lee et al. proposed a secure key issuing protocol. However we show that it suffers from impersonation, insider attacks and incompetency of the key privacy authorities. We also cryptanalyze Sui et al.'s separable and anonymous key issuing protocol.

cs.CR↗

arXiv2005

Gossip Codes for Fingerprinting: Construction, Erasure Analysis and Pirate Tracing

This work presents two new construction techniques for q-ary Gossip codes from tdesigns and Traceability schemes. These Gossip codes achieve the shortest code length specified in terms of code parameters and can withstand erasures in digital fingerprinting applications. This work presents the construction of embedded Gossip codes for extending an existing Gossip code into a bigger code. It discusses the construction of concatenated codes and realisation of erasure model through concatenated codes.

cs.CR↗