ATRS uses a shared neural policy in a multi-agent MDP to adaptively re-split trajectory segments during parallel ADMM optimization, cutting iterations by up to 26% and time by 19.1% with zero-shot generalization.
hub
Fast-lio2: Fast direct lidar- inertial odometry
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
fields
cs.RO 13roles
method 1polarities
use method 1representative citing papers
OptMap generates compact, application-specific geometric maps from streaming LiDAR data using a novel submodular reward function and a dynamically reordered streaming maximization algorithm.
Introduces an incremental reachable graph and structural priors for multi-floor ground robot exploration, showing improved efficiency in simulation and real-time onboard performance.
FU-MPC is a receding-horizon MPC controller that treats motorized LiDAR rotation as an explicit variable to jointly maximize frontier exploration utility and minimize direction-dependent localization uncertainty during UAV flight.
ASIP-Planner achieves near-complete surface coverage and shorter trajectories in partially known indoor environments by clustering inspection targets globally and adapting viewing angles locally to handle occlusions.
X-IONet combines rule-based platform classification with a dual-stage attention network to predict displacement and uncertainty from IMU data, then fuses outputs via EKF, achieving reported error reductions on pedestrian and quadruped datasets.
Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.
Local normal-vector constraints plus degeneracy-guided map updates cut solid-state LiDAR-inertial odometry RMSE by up to 12.8% in extreme, geometrically degenerate environments.
IGV-RRT improves object goal navigation in dynamic indoor environments by combining uncertainty-aware priors from 3D scene graphs with online VLM observations in a real-time tree planner.
ADM-Fusion proposes an end-to-end adaptive multi-sensor fusion network using mixture-of-experts routing and cross-task attention for robust ego-motion estimation, trained on simulation then fine-tuned on real data.
A highway-focused AV localization system decouples LiDAR geometric and texture cues, augments EKF with steering and acceleration commands, and releases a 163 km public dataset showing superior robustness over baselines in challenging conditions.
MacroNav learns multi-scale navigation-centric representations through multi-task self-supervised learning and combines them with graph-based reinforcement learning for efficient action selection, reporting gains in success rate and path efficiency over prior methods.
DRLACP applies SAC with GRUs to learn cooperative planning actions for AVs under imperfect state information and shows better performance than baselines in CARLA simulations.
citing papers explorer
-
ATRS: Adaptive Trajectory Re-splitting via a Shared Neural Policy for Parallel Optimization
ATRS uses a shared neural policy in a multi-agent MDP to adaptively re-split trajectory segments during parallel ADMM optimization, cutting iterations by up to 26% and time by 19.1% with zero-shot generalization.
-
OptMap: Geometric Map Distillation via Submodular Maximization
OptMap generates compact, application-specific geometric maps from streaming LiDAR data using a novel submodular reward function and a dynamically reordered streaming maximization algorithm.
-
Multi-Floor Exploration for Ground Robots via an Incremental Reachable Graph and Structural Priors
Introduces an incremental reachable graph and structural priors for multi-floor ground robot exploration, showing improved efficiency in simulation and real-time onboard performance.
-
FU-MPC: Frontier- and Uncertainty-Aware Model Predictive Control for Efficient and Accurate UAV Exploration with Motorized LiDAR
FU-MPC is a receding-horizon MPC controller that treats motorized LiDAR rotation as an explicit variable to jointly maximize frontier exploration utility and minimize direction-dependent localization uncertainty during UAV flight.
-
ASIP-Planner: Adaptive Planning for UAV Surface Inspection in Partially Known Indoor Environments
ASIP-Planner achieves near-complete surface coverage and shorter trajectories in partially known indoor environments by clustering inspection targets globally and adapting viewing angles locally to handle occlusions.
-
X-IONet: Cross-Platform Inertial Odometry Network for Pedestrian and Legged Robot
X-IONet combines rule-based platform classification with a dual-stage attention network to predict displacement and uncertainty from IMU data, then fuses outputs via EKF, achieving reported error reductions on pedestrian and quadruped datasets.
-
Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy
Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.
-
Environment-Adaptive Solid-State LiDAR-Inertial Odometry
Local normal-vector constraints plus degeneracy-guided map updates cut solid-state LiDAR-inertial odometry RMSE by up to 12.8% in extreme, geometrically degenerate environments.
-
IGV-RRT: Prior-Real-Time Observation Fusion for Active Object Search in Changing Environments
IGV-RRT improves object goal navigation in dynamic indoor environments by combining uncertainty-aware priors from 3D scene graphs with online VLM observations in a real-time tree planner.
-
ADM-Fusion: Adaptive Deep Multi-Sensor Fusion for Robust Ego-Motion Estimation in Diverse Conditions
ADM-Fusion proposes an end-to-end adaptive multi-sensor fusion network using mixture-of-experts routing and cross-task attention for robust ego-motion estimation, trained on simulation then fine-tuned on real data.
-
Robust Localization for Autonomous Vehicles in Highway Scenes
A highway-focused AV localization system decouples LiDAR geometric and texture cues, augments EKF with steering and acceleration commands, and releases a 163 km public dataset showing superior robustness over baselines in challenging conditions.
-
MacroNav: Multi-Task Context Representation Learning Enables Efficient Navigation in Unknown Environments
MacroNav learns multi-scale navigation-centric representations through multi-task self-supervised learning and combines them with graph-based reinforcement learning for efficient action selection, reporting gains in success rate and path efficiency over prior methods.
-
Unveiling Uncertainty-Aware Autonomous Cooperative Learning Based Planning Strategy
DRLACP applies SAC with GRUs to learn cooperative planning actions for AVs under imperfect state information and shows better performance than baselines in CARLA simulations.