Kostas Daniilidis

About

Kostas Daniilidis is the Ruth Yalom Stone Professor at the University of Pennsylvania, where he is a faculty member in the Department of Computer and Information Science within the School of Engineering and Applied Science. He leads the GRASP Laboratory and is also affiliated with the Archimedes Athena Research Center in Greece. His academic background includes a PhD from the University of Karlsruhe in 1992 under the supervision of Hans-Hellmut Nagel, and a Diploma (Integrated Master's) in Electrical Engineering from the National Technical University of Athens in 1986. Daniilidis's research focuses on computer vision and robotics, as indicated by his leadership of the GRASP Laboratory and his extensive involvement in teaching courses related to machine perception, robotics, and computer architecture. Throughout his career, he has mentored numerous PhD students, postdoctoral researchers, and alumni who have gone on to positions in academia and industry. His work is supported by multiple grants from agencies such as the NSF, ARL, ARO, and ONR, reflecting his active engagement in advancing research in his fields of expertise.

Research topics

• Artificial Intelligence
• Computer Science
• Computer vision
• Machine Learning
• Mathematics
• Human–computer interaction

Selected publications

• Event-Based Vision: A Survey

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2020 · 632 citations

  Event cameras are bio-inspired sensors that differ from conventional frame cameras: Instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes, and output a stream of events that encode the time, location and sign of the brightness changes. Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of is), very high dynamic range (140dB vs. 60dB), low power consumption, and high pixel bandwidth (on…

  DOI

• Reactive Semantic Planning in Unexplored Semantic Environments Using Deep Perceptual Feedback

  IEEE Robotics and Automation Letters · 2020 · 32 citations

  This letter presents a reactive planning system that enriches the topological representation of an environment with a tightly integrated semantic representation, achieved by incorporating and exploiting advances in deep perceptual learning and probabilistic semantic reasoning. Our architecture combines object detection with semantic SLAM, affording robust, reactive logical as well as geometric planning in unexplored environments. Moreover, by incorporating a human mesh estimation algorithm, our…

  DOI

• Next Best Sense: Guiding Vision and Touch with FisherRF for 3D Gaussian Splatting

  2025-05-19 · 2 citations

  article

  We propose a framework for active next best view and touch selection for robotic manipulators using 3D Gaussian Splatting (3DGS). 3DGS is emerging as a useful explicit 3D scene representation for robotics, as it has the ability to represent scenes in a both photorealistic and geometrically accurate manner. However, in real-world, online robotic scenes where the number of views is limited given efficiency requirements, random view selection for 3DGS becomes impractical as views are often overlapp…

  PublisherDOI

• Active Next-Best-View Optimization for Risk-Averse Path Planning

  ArXiv.org · 2025-10-07 · 1 citations

  preprintOpen access

  Safe navigation in uncertain environments requires planning methods that integrate risk aversion with active perception. In this work, we present a unified framework that refines a coarse reference path by constructing tail-sensitive risk maps from Average Value-at-Risk statistics on an online-updated 3D Gaussian-splat Radiance Field. These maps enable the generation of locally safe and feasible trajectories. In parallel, we formulate Next-Best-View (NBV) selection as an optimization problem on…

  PublisherOA PDFDOI

• EV-TTC: Event-Based Time to Collision Under Low Light Conditions

  IEEE Robotics and Automation Letters · 2025-04-28 · 1 citations

  articleSenior author

  Rapid and accurate dense time-to-collision (TTC) estimation in resource-constrained, low-light environments is challenging for event-based camera systems. Fixed-time event representations like voxel grids face an inherent trade-off: larger temporal windows improve perception accuracy but increase storage demands, while smaller windows reduce storage at the cost of accuracy. We present a hardware-aware TTC estimation system designed for mobile robots, satisfying strict bandwidth, computation, and…

  PublisherDOI

Recent grants

• CDI-Type II: Collaborative Research: Cyber Enhancement of Spatial Cognition for the Visually Impaired

  NSF · $462k · 2008–2012

• RI: Collaborative Research: Bio-inspired Navigation

  NSF · $225k · 2007–2010

• I/UCRC Phase I: Robots and Sensors for the Human Well-being

  NSF · $260k · 2014–2019

Frequent coauthors

• Xiaowei Zhou

  44 shared

• Georgios Pavlakos

  44 shared

• Karl Schmeckpeper

  University of Pennsylvania

  35 shared

• Oleh Rybkin

  31 shared

• Ameesh Makadia

  Google (United States)

  30 shared

• Alex Zihao Zhu

  29 shared

• Konstantinos G. Derpanis

  York University

  25 shared

• Carlos Esteves

  Google (United States)

  23 shared

Labs

• GRASP LaboratoryPI

Education

• Ph.D., Computer Science

  University of California, Berkeley

  1995

• M.S., Computer Science

  University of California, Berkeley

  1991

• B.S., Electrical Engineering

  University of California, Los Angeles

  1988

Awards & honors

• Best Conference Paper Award, IEEE International Conference o…
• Fellow of the IEEE (2012)

Similar researchers at University of Pennsylvania

• Vijay Kumarh-67
• Junhyong Kimh-62
• Daniel Hopkinsh-40