Nachiket Deo
YOU?
Author Swipe
View article: PBP: Path-based Trajectory Prediction for Autonomous Driving
PBP: Path-based Trajectory Prediction for Autonomous Driving Open
Trajectory prediction plays a crucial role in the autonomous driving stack by enabling autonomous vehicles to anticipate the motion of surrounding agents. Goal-based prediction models have gained traction in recent years for addressing the…
View article: Salient Sign Detection In Safe Autonomous Driving: AI Which Reasons Over Full Visual Context
Salient Sign Detection In Safe Autonomous Driving: AI Which Reasons Over Full Visual Context Open
Detecting road traffic signs and accurately determining how they can affect the driver's future actions is a critical task for safe autonomous driving systems. However, various traffic signs in a driving scene have an unequal impact on the…
View article: Safe Control Transitions: Machine Vision Based Observable Readiness Index and Data-Driven Takeover Time Prediction
Safe Control Transitions: Machine Vision Based Observable Readiness Index and Data-Driven Takeover Time Prediction Open
To make safe transitions from autonomous to manual control, a vehicle must have a representation of the awareness of driver state; two metrics which quantify this state are the Observable Readiness Index and Takeover Time. In this work, we…
View article: Runtime provenance refinement for notebooks
Runtime provenance refinement for notebooks Open
Computational notebooks (e.g., Jupyter or Apache Zeppelin) have become a popular choice for data exploration, preparation, and ETL. Notebooks are more suited for interactive development of data pipelines than classical workflow systems, be…
View article: On Salience-Sensitive Sign Classification in Autonomous Vehicle Path Planning: Experimental Explorations with a Novel Dataset
On Salience-Sensitive Sign Classification in Autonomous Vehicle Path Planning: Experimental Explorations with a Novel Dataset Open
Safe path planning in autonomous driving is a complex task due to the interplay of static scene elements and uncertain surrounding agents. While all static scene elements are a source of information, there is asymmetric importance to the i…
View article: Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling with Real-World Data
Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling with Real-World Data Open
With increasing automation in passenger vehicles, the study of safe and smooth occupant-vehicle interaction and control transitions is key. In this study, we focus on the development of contextual, semantically meaningful representations o…
View article: Predicting Take-over Time for Autonomous Driving with Real-World Data: Robust Data Augmentation, Models, and Evaluation
Predicting Take-over Time for Autonomous Driving with Real-World Data: Robust Data Augmentation, Models, and Evaluation Open
Understanding occupant-vehicle interactions by modeling control transitions is important to ensure safe approaches to passenger vehicle automation. Models which contain contextual, semantically meaningful representations of driver states c…
View article: Predicting Take-over Time for Autonomous Driving with Real-World Data:\n Robust Data Augmentation, Models, and Evaluation
Predicting Take-over Time for Autonomous Driving with Real-World Data:\n Robust Data Augmentation, Models, and Evaluation Open
Understanding occupant-vehicle interactions by modeling control transitions\nis important to ensure safe approaches to passenger vehicle automation. Models\nwhich contain contextual, semantically meaningful representations of driver\nstate…
View article: Trajectory Prediction for Autonomous Driving based on Multi-Head Attention with Joint Agent-Map Representation
Trajectory Prediction for Autonomous Driving based on Multi-Head Attention with Joint Agent-Map Representation Open
Predicting the trajectories of surrounding agents is an essential ability for autonomous vehicles navigating through complex traffic scenes. The future trajectories of agents can be inferred using two important cues: the locations and past…
View article: Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals
Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals Open
Accurately predicting the future motion of surrounding vehicles requires reasoning about the inherent uncertainty in driving behavior. This uncertainty can be loosely decoupled into lateral (e.g., keeping lane, turning) and longitudinal (e…
View article: Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling\n with Real-World Data
Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling\n with Real-World Data Open
With increasing automation in passenger vehicles, the study of safe and\nsmooth occupant-vehicle interaction and control transitions is key. In this\nstudy, we focus on the development of contextual, semantically meaningful\nrepresentation…
View article: Trajectory Prediction in Autonomous Driving With a Lane Heading Auxiliary Loss
Trajectory Prediction in Autonomous Driving With a Lane Heading Auxiliary Loss Open
Predicting a vehicle's trajectory is an essential ability for autonomous vehicles navigating through complex urban traffic scenes. Bird's-eye-view roadmap information provides valuable information for making trajectory predictions, and whi…
View article: Trajectory Prediction in Autonomous Driving with a Lane Heading\n Auxiliary Loss
Trajectory Prediction in Autonomous Driving with a Lane Heading\n Auxiliary Loss Open
Predicting a vehicle's trajectory is an essential ability for autonomous\nvehicles navigating through complex urban traffic scenes. Bird's-eye-view\nroadmap information provides valuable information for making trajectory\npredictions, and …
View article: Trajectory Prediction for Autonomous Driving based on Multi-Head\n Attention with Joint Agent-Map Representation
Trajectory Prediction for Autonomous Driving based on Multi-Head\n Attention with Joint Agent-Map Representation Open
Predicting the trajectories of surrounding agents is an essential ability for\nautonomous vehicles navigating through complex traffic scenes. The future\ntrajectories of agents can be inferred using two important cues: the locations\nand p…
View article: Scene Compliant Trajectory Forecast With Agent-Centric Spatio-Temporal Grids
Scene Compliant Trajectory Forecast With Agent-Centric Spatio-Temporal Grids Open
Forecasting long-term human motion is a challenging task due to the non-linearity, multi-modality and inherent uncertainty in future trajectories. The underlying scene and past motion of agents can provide useful cues to predict their futu…
View article: Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans
Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Plans Open
We address the problem of forecasting pedestrian and vehicle trajectories in unknown environments, conditioned on their past motion and scene structure. Trajectory forecasting is a challenging problem due to the large variation in scene st…
View article: Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over Readiness
Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over Readiness Open
Continuous estimation the driver's take-over readiness is critical for safe and timely transfer of control during the failure modes of autonomous vehicles. In this paper, we propose a data-driven approach for estimating the driver's take-o…
View article: Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal\n Grids
Scene Compliant Trajectory Forecast with Agent-Centric Spatio-Temporal\n Grids Open
Forecasting long-term human motion is a challenging task due to the\nnon-linearity, multi-modality and inherent uncertainty in future trajectories.\nThe underlying scene and past motion of agents can provide useful cues to\npredict their f…
View article: Understanding Pedestrian-Vehicle Interactions with Vehicle Mounted Vision: An LSTM Model and Empirical Analysis
Understanding Pedestrian-Vehicle Interactions with Vehicle Mounted Vision: An LSTM Model and Empirical Analysis Open
Pedestrians and vehicles often share the road in complex inner city traffic. This leads to interactions between the vehicle and pedestrians, with each affecting the other's motion. In order to create robust methods to reason about pedestri…
View article: Scene Induced Multi-Modal Trajectory Forecasting via Planning
Scene Induced Multi-Modal Trajectory Forecasting via Planning Open
We address multi-modal trajectory forecasting of agents in unknown scenes by formulating it as a planning problem. We present an approach consisting of three models; a goal prediction model to identify potential goals of the agent, an inve…
View article: Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over\n Readiness
Looking at the Driver/Rider in Autonomous Vehicles to Predict Take-Over\n Readiness Open
Continuous estimation the driver's take-over readiness is critical for safe\nand timely transfer of control during the failure modes of autonomous vehicles.\nIn this paper, we propose a data-driven approach for estimating the driver's\ntak…
View article: Audio segmentation based on melodic style with hand-crafted features and with convolutional neural networks
Audio segmentation based on melodic style with hand-crafted features and with convolutional neural networks Open
We investigate methods for the automatic labeling of the taan section, a prominent structural component of the Hindustani Khayal vocal concert. The taan contains improvised raga-based melody rendered in the highly distinctive style of rapi…
View article: Convolutional Social Pooling for Vehicle Trajectory Prediction
Convolutional Social Pooling for Vehicle Trajectory Prediction Open
Forecasting the motion of surrounding vehicles is a critical ability for an autonomous vehicle deployed in complex traffic. Motion of all vehicles in a scene is governed by the traffic context, i.e., the motion and relative spatial configu…
View article: How Would Surround Vehicles Move? A Unified Framework for Maneuver Classification and Motion Prediction
How Would Surround Vehicles Move? A Unified Framework for Maneuver Classification and Motion Prediction Open
Reliable prediction of surround vehicle motion is a critical requirement for\npath planning for autonomous vehicles. In this paper we propose a unified\nframework for surround vehicle maneuver classification and motion prediction\nthat exp…
View article: Late-Materialization using Sort-merge Join Algorithm
Late-Materialization using Sort-merge Join Algorithm Open
In this paper, we study the use of Late-materialization for sort-merge join algorithm.We study various effects of using this strategy and also compare it with other techniques like pipelining.
View article: Performance Review System – An ERP Application with Secure Data Storage and Cloud Backup
Performance Review System – An ERP Application with Secure Data Storage and Cloud Backup Open
Traditionally we have seen that ERP systems are developed using Row-oriented database system.Our project tries to implement column-oriented approach in development of ERP systems.The system which we are trying to develop is Employee Perfor…