Search Results for author: Siddharth Srivastava

Found 50 papers, 10 papers with code

Belief-State Query Policies for Planning With Preferences Under Partial Observability

no code implementations24 May 2024 Daniel Bramblett, Siddharth Srivastava

Empirical results show that BSQ preferences provide a computationally feasible approach for planning with preferences in partially observable settings.

Can LLMs Converse Formally? Automatically Assessing LLMs in Translating and Interpreting Formal Specifications

no code implementations27 Mar 2024 Rushang Karia, Daksh Dobhal, Daniel Bramblett, Pulkit Verma, Siddharth Srivastava

Stakeholders often describe system requirements using natural language which are then converted to formal syntax by a domain-expert leading to increased design costs.


From Reals to Logic and Back: Inventing Symbolic Vocabularies, Actions, and Models for Planning from Raw Data

no code implementations19 Feb 2024 Naman Shah, Jayesh Nagpal, Pulkit Verma, Siddharth Srivastava

Empirical results in deterministic settings show that powerful abstract representations can be learned from just a handful of robot trajectories; the learned relational representations include but go beyond classical, intuitive notions of high-level actions; and that the learned models allow planning algorithms to scale to tasks that were previously beyond the scope of planning without hand-crafted abstractions.

Motion Planning Task and Motion Planning

Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Settings

no code implementations13 Feb 2024 Rushang Karia, Pulkit Verma, Alberto Speranzon, Siddharth Srivastava

This paper introduces a new approach for continual planning and model learning in relational, non-stationary stochastic environments.

Decision Making

OmniVec: Learning robust representations with cross modal sharing

no code implementations7 Nov 2023 Siddharth Srivastava, Gaurav Sharma

We demonstrate empirically that, using a joint network to train across modalities leads to meaningful information sharing and this allows us to achieve state-of-the-art results on most of the benchmarks.

 Ranked #1 on Image Classification on ImageNet (using extra training data)

3D Point Cloud Classification Action Classification +3

Predicting Citi Bike Demand Evolution Using Dynamic Graphs

1 code implementation18 Dec 2022 Alexander Saff, Mayur Bhandary, Siddharth Srivastava

In this paper, we attempt to apply a graph neural network model to predict bike demand in the New York City, Citi Bike dataset.

Graph Neural Network Management

Hierarchical Decomposition and Analysis for Generalized Planning

no code implementations6 Dec 2022 Siddharth Srivastava

These methods can be used to determine the utility of a given generalized plan, as well as to guide the synthesis and learning processes for generalized plans.

Multi-Task Option Learning and Discovery for Stochastic Path Planning

no code implementations30 Sep 2022 Naman Shah, Siddharth Srivastava

This paper addresses the problem of reliably and efficiently solving broad classes of long-horizon stochastic path planning problems.

Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems

no code implementations27 Apr 2022 Rushang Karia, Siddharth Srivastava

Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons.

Object reinforcement-learning +1

Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems

1 code implementation8 Apr 2022 Rushang Karia, Rashmeet Kaur Nayyar, Siddharth Srivastava

Several goal-oriented problems in the real-world can be naturally expressed as Stochastic Shortest Path Problems (SSPs).

Differential Assessment of Black-Box AI Agents

1 code implementation24 Mar 2022 Rashmeet Kaur Nayyar, Pulkit Verma, Siddharth Srivastava

In this work, we propose a novel approach to "differentially" assess black-box AI agents that have drifted from their previously known models.

Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

no code implementations2 Feb 2022 Naman Shah, Siddharth Srivastava

This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability.

Beyond Mono to Binaural: Generating Binaural Audio from Mono Audio with Depth and Cross Modal Attention

no code implementations15 Nov 2021 Kranti Kumar Parida, Siddharth Srivastava, Gaurav Sharma

In this work, we argue that depth map of the scene can act as a proxy for inducing distance information of different objects in the scene, for the task of audio binauralization.


JEDAI: A System for Skill-Aligned Explainable Robot Planning

1 code implementation31 Oct 2021 Naman Shah, Pulkit Verma, Trevor Angle, Siddharth Srivastava

This paper presents JEDAI, an AI system designed for outreach and educational efforts aimed at non-AI experts.

Decision Making Motion Planning +1

Learning Causal Models of Autonomous Agents using Interventions

no code implementations21 Aug 2021 Pulkit Verma, Siddharth Srivastava

One of the several obstacles in the widespread use of AI systems is the lack of requirements of interpretability that can enable a layperson to ensure the safe and reliable behavior of such systems.

Depth Infused Binaural Audio Generation using Hierarchical Cross-Modal Attention

no code implementations10 Aug 2021 Kranti Kumar Parida, Siddharth Srivastava, Neeraj Matiyali, Gaurav Sharma

Binaural audio gives the listener the feeling of being in the recording place and enhances the immersive experience if coupled with AR/VR.

Audio Generation Decoder

Discovering User-Interpretable Capabilities of Black-Box Planning Agents

1 code implementation28 Jul 2021 Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava

Starting from a set of user-interpretable state properties, an AI agent, and a simulator that the agent can interact with, our algorithm returns a set of high-level capabilities with their parameterized descriptions.

AI Agent Decision Making

Planning for Proactive Assistance in Environments with Partial Observability

no code implementations2 May 2021 Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

This paper addresses the problem of synthesizing the behavior of an AI agent that provides proactive task assistance to a human in settings like factory floors where they may coexist in a common environment.

AI Agent

Beyond Image to Depth: Improving Depth Prediction using Echoes

1 code implementation CVPR 2021 Kranti Kumar Parida, Siddharth Srivastava, Gaurav Sharma

We propose a novel multi modal fusion technique, which incorporates the material properties explicitly while combining audio (echoes) and visual modalities to predict the scene depth.

Depth Estimation Depth Prediction

Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations

no code implementations ICLR 2022 Sarath Sreedharan, Utkarsh Soni, Mudit Verma, Siddharth Srivastava, Subbarao Kambhampati

As increasingly complex AI systems are introduced into our daily lives, it becomes important for such systems to be capable of explaining the rationale for their decisions and allowing users to contest these decisions.

Decision Making Montezuma's Revenge

Asking the Right Questions: Learning Interpretable Action Models Through Query Answering

1 code implementation29 Dec 2019 Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava

This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act.

Signaling Friends and Head-Faking Enemies Simultaneously: Balancing Goal Obfuscation and Goal Legibility

no code implementations25 May 2019 Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

In order to be useful in the real world, AI agents need to plan and act in the presence of others, who may include adversarial and cooperative entities.

An Online Learning Approach for Dengue Fever Classification

no code implementations17 Apr 2019 Siddharth Srivastava, Sumit Soman, Astha Rai

This paper introduces a novel approach for dengue fever classification based on online learning paradigms.

Classification General Classification

Few Shot Speaker Recognition using Deep Neural Networks

no code implementations17 Apr 2019 Prashant Anand, Ajeet Kumar Singh, Siddharth Srivastava, Brejesh lall

The recent advances in deep learning are mostly driven by availability of large amount of training data.

Few-Shot Learning Speaker Recognition

DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds

no code implementations27 Mar 2019 Siddharth Srivastava, Brejesh lall

The method constitutes a deep network for learning permutation invariant representation of 3D points.

Metric Learning

Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms

no code implementations ICML 2018 Yi Wu, Siddharth Srivastava, Nicholas Hay, Simon Du, Stuart Russell

Despite the recent successes of probabilistic programming languages (PPLs) in AI applications, PPLs offer only limited support for random variables whose distributions combine discrete and continuous elements.

Probabilistic Programming

Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations

no code implementations19 Feb 2018 Sarath Sreedharan, Siddharth Srivastava, Subbarao Kambhampati

There is a growing interest within the AI research community to develop autonomous systems capable of explaining their behavior to users.

Explanation Generation

An Anytime Algorithm for Task and Motion MDPs

no code implementations16 Feb 2018 Siddharth Srivastava, Nishant Desai, Richard Freedman, Shlomo Zilberstein

We present a new approach where the high-level decision problem occurs in a stochastic setting and can be modeled as a Markov decision process.

Decision Making Motion Planning +1

A Unified Framework for Planning in Adversarial and Cooperative Environments

no code implementations16 Feb 2018 Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

By slightly varying our framework, we present an approach for goal legibility in cooperative settings which produces plans that achieve a goal while being consistent with at most j goals from a set of confounding goals.

Drought Stress Classification using 3D Plant Models

no code implementations21 Sep 2017 Siddharth Srivastava, Swati Bhugra, Brejesh lall, Santanu Chaudhury

Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner.

3D Reconstruction Classification +1

3D Binary Signatures

no code implementations26 Aug 2017 Siddharth Srivastava, Brejesh lall

3DBS describes keypoints from point clouds with a binary vector resulting in extremely fast matching.

Learning Generalized Reactive Policies using Deep Neural Networks

no code implementations24 Aug 2017 Edward Groshev, Maxwell Goldstein, Aviv Tamar, Siddharth Srivastava, Pieter Abbeel

We show that a deep neural network can be used to learn and represent a \emph{generalized reactive policy} (GRP) that maps a problem instance and a state to an action, and that the learned GRPs efficiently solve large classes of challenging problem instances.

Decision Making feature selection

Large Scale Novel Object Discovery in 3D

no code implementations22 Jan 2017 Siddharth Srivastava, Gaurav Sharma, Brejesh lall

We test on unknown objects, which were not seen during training, and perform clustering in the learned embedding space of supervoxels to effectively perform novel object discovery.

Clustering Object +1

Benchmarking KAZE and MCM for Multiclass Classification

no code implementations20 May 2015 Siddharth Srivastava, Prerana Mukherjee, Brejesh lall

In this paper, we propose a novel approach for feature generation by appropriately fusing KAZE and SIFT features.

Benchmarking Classification +1

SIFT Vs SURF: Quantifying the Variation in Transformations

no code implementations25 Apr 2015 Siddharth Srivastava

This paper studies the robustness of SIFT and SURF against different image transforms (rigid body, similarity, affine and projective) by quantitatively analyzing the variations in the extent of transformations.

Cannot find the paper you are looking for? You can Submit a new open access paper.