Not all neuro-symbolic concepts are created equal: Analysis and mitigation of reasoning shortcuts
Abstract Neuro-Symbolic (NeSy) predictive models hold the promise of improved
compliance with given constraints, systematic generalization, and interpretability, as they …
compliance with given constraints, systematic generalization, and interpretability, as they …
Gama: Generative adversarial multi-object scene attacks
The majority of methods for crafting adversarial attacks have focused on scenes with a
single dominant object (eg, images from ImageNet). On the other hand, natural scenes …
single dominant object (eg, images from ImageNet). On the other hand, natural scenes …
WOODS: Benchmarks for out-of-distribution generalization in time series
Machine learning models often fail to generalize well under distributional shifts.
Understanding and overcoming these failures have led to a research field of Out-of …
Understanding and overcoming these failures have led to a research field of Out-of …
Near-field perception for low-speed vehicle automation using surround-view fisheye cameras
Cameras are the primary sensor in automated driving systems. They provide high
information density and are optimal for detecting road infrastructure cues laid out for human …
information density and are optimal for detecting road infrastructure cues laid out for human …
A residual convolutional neural network based approach for real-time path planning
Path planning for unmanned aerial vehicles (UAVs) has been widely considered in various
tasks. Existing path planning algorithms, such as A* and Jump Point Search, have been …
tasks. Existing path planning algorithms, such as A* and Jump Point Search, have been …
Autonomous field management–An enabler of sustainable future in agriculture
CONTEXT Technological innovations in agriculture are mainly driven by the maxim:
increase productivity at any costs. Today, in the face of climate change and an …
increase productivity at any costs. Today, in the face of climate change and an …
[HTML][HTML] Towards the unified principles for level 5 autonomous vehicles
The rapid advance of autonomous vehicles (AVs) has motivated new perspectives and
potential challenges for existing modes of transportation. Currently, driving assistance …
potential challenges for existing modes of transportation. Currently, driving assistance …
What is missing in autonomous discovery: open challenges for the community
Self-driving labs (SDLs) leverage combinations of artificial intelligence, automation, and
advanced computing to accelerate scientific discovery. The promise of this field has given …
advanced computing to accelerate scientific discovery. The promise of this field has given …
Attention for vision-based assistive and automated driving: A review of algorithms and datasets
I Kotseruba, JK Tsotsos - IEEE transactions on intelligent …, 2022 - ieeexplore.ieee.org
Driving safety has been a concern since the first cars appeared on the streets. Driver
inattention has been singled out as a major cause of accidents early on. This is hardly …
inattention has been singled out as a major cause of accidents early on. This is hardly …
Lightweight object detection ensemble framework for autonomous vehicles in challenging weather conditions
The computer vision systems driving autonomous vehicles are judged by their ability to
detect objects and obstacles in the vicinity of the vehicle in diverse environments. Enhancing …
detect objects and obstacles in the vicinity of the vehicle in diverse environments. Enhancing …