RESOLVE provides a controlled multi-resolution LiDAR and camera benchmark for evaluating 3D detection and tracking under point sparsity variations in roadside cooperative perception.
hub
In: Proceedings of the 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), pp
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
representative citing papers
RS2AD-LiDAR reconstructs vehicle LiDAR data from roadside observations via coordinate transformation, virtual LiDAR modeling and resampling, claimed as the first such method, with experiments showing improved object detection when mixed with real data.
GROSS is an open pipeline generating nation-scale German rail scenarios for SUMO via topology-aware stop mapping from OSM and GTFS, reducing teleportations 1.7-76.8x versus prior methods.
ARCANE-PedSynth is a CARLA-based framework that generates synthetic multi-pedestrian datasets with behavioral crossing annotations by using hybrid AI-manual control to raise crossing rates and a 12-state FSM for diverse behaviors.
MR-LiDAR benchmark shows an 80-beam LiDAR with optimized distribution can match or exceed 128-beam uniform LiDAR for roadside vehicle and VRU detection.
LiloDriver uses LLMs and memory-augmented planning in a four-stage pipeline to outperform rule-based and learning-based methods on both common and rare scenarios in the nuPlan benchmark.
A tensor-network encoding of TSP tours with Boltzmann weighting and explicit constraint filters that supplies a marginal formula for optimal tours in the zero-temperature exact limit.
Presents a geo-data-driven workflow that generates lane-level HD maps from open shapefile road data and verifies them via executable constraints derived from automated driving specifications and road design guidelines.
Active inference model unifies human collision avoidance by reproducing meta-analysis aggregates and simulator-specific effects on response timing, maneuver selection, and execution.
A pose-conditioned predictive denoiser for multi-anchor UWB ranging improves work zone geometry reconstruction and reduces field MSE by 66.9% relative to raw input in NLOS conditions.
Applies conformalized quantile regression with equalized coverage to predict motion control performance in automated vehicles under nominal, degraded, and failed actuator conditions.
LLM-assisted pipeline jointly generates logical formulas and executable predicates for rule-based verification of HD map transformations in CommonRoad, evaluated on synthetic bridge and slope scenarios.
citing papers explorer
-
RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception
RESOLVE provides a controlled multi-resolution LiDAR and camera benchmark for evaluating 3D detection and tracking under point sparsity variations in roadside cooperative perception.
-
RS2AD-LiDAR: End-to-End Autonomous Driving LiDAR Data Generation from Roadside Sensor Observations
RS2AD-LiDAR reconstructs vehicle LiDAR data from roadside observations via coordinate transformation, virtual LiDAR modeling and resampling, claimed as the first such method, with experiments showing improved object detection when mixed with real data.
-
GROSS: German Rail Open-Source SUMO Scenario
GROSS is an open pipeline generating nation-scale German rail scenarios for SUMO via topology-aware stop mapping from OSM and GTFS, reducing teleportations 1.7-76.8x versus prior methods.
-
ARCANE-PedSynth: Synthetic Multi-Pedestrian Datasets with Behavioural Crossing Annotations
ARCANE-PedSynth is a CARLA-based framework that generates synthetic multi-pedestrian datasets with behavioral crossing annotations by using hybrid AI-manual control to raise crossing rates and a 12-state FSM for diverse behaviors.
-
MR-LiDAR: A Multi-Resolution Roadside LiDAR Benchmark for Perception Diagnostics and Deployment Guidance
MR-LiDAR benchmark shows an 80-beam LiDAR with optimized distribution can match or exceed 128-beam uniform LiDAR for roadside vehicle and VRU detection.
-
LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
LiloDriver uses LLMs and memory-augmented planning in a four-stage pipeline to outperform rule-based and learning-based methods on both common and rare scenarios in the nuPlan benchmark.
-
Tensor-Network Formulation of the Traveling Salesman Problem and Variants
A tensor-network encoding of TSP tours with Boltzmann weighting and explicit constraint filters that supplies a marginal formula for optimal tours in the zero-temperature exact limit.
-
Geo-Data-Driven HD Map Generation Workflow with Integrated Reference-Free Constraint-Based Verification
Presents a geo-data-driven workflow that generates lane-level HD maps from open shapefile road data and verifies them via executable constraints derived from automated driving specifications and road design guidelines.
-
Active inference as a unified model of collision avoidance behavior in human drivers
Active inference model unifies human collision avoidance by reproducing meta-analysis aggregates and simulator-specific effects on response timing, maneuver selection, and execution.
-
V2I Work Zone Geometry Reconstruction with Pose-Conditioned UWB Range Denoising
A pose-conditioned predictive denoiser for multi-anchor UWB ranging improves work zone geometry reconstruction and reduces field MSE by 66.9% relative to raw input in NLOS conditions.
-
Equalized Coverage in Motion Control Performance Prediction for Self-Adaptive Road Vehicles
Applies conformalized quantile regression with equalized coverage to predict motion control performance in automated vehicles under nominal, degraded, and failed actuator conditions.
-
LLM-Assisted Tool for Joint Generation of Formulas and Functions in Rule-Based Verification of Map Transformations
LLM-assisted pipeline jointly generates logical formulas and executable predicates for rule-based verification of HD map transformations in CommonRoad, evaluated on synthetic bridge and slope scenarios.