Multi-modal deep learning model achieves 85% accuracy in pedestrian intent prediction, enhancing autonomous driving safety.

Amir Rasouli, John K. Tsotsos

Proposes a sparse 3D topological graph for MAV planning, using GPU-accelerated GVD extraction and skeletonization to enable fast, robust pathfinding in noisy environments.

Helen Oleynikova, Zachary Taylor, Roland Siegwart et al.

Proposes asymmetric Actor-Critic leveraging full states during training and visual inputs at inference, achieving robust sim-to-real transfer without real data.

Lerrel Pinto, Marcin Andrychowicz, Peter Welinder et al.

Combining domain randomization with generative autoregressive models, achieving over 90% success on unseen objects in robotic grasping.

Joshua Tobin, Lukas Biewald, Rocky Duan et al.

Proposes an incremental deep Boltzmann machine for adaptive hierarchical scene context modeling, dynamically adding layers based on confidence measures.

Fethiye Irmak Doğan, Hande Çelikkanat, Sinan Kalkan

Social Attention learns nonlocal pedestrian importance, reducing mean ADE to 0.30 m and FDE to 2.59 m on ETH/UCY.

Anirudh Vemula, Katharina Muelling, Jean Oh

Proposes conditional imitation learning with high-level commands, enabling end-to-end autonomous driving with improved controllability and robustness.

Felipe Codevilla, Matthias Müller, Antonio López et al.

Ergodic exploration (EEDI) optimizes trajectories to match expected information density, outperforming traditional info-max controls in nonlinear systems.

Lauren M. Miller, Yonatan Silverman, Malcolm A. MacIver et al.

Proposes a grasp pose detection method in point clouds, achieving a 93% success rate.

Andreas ten Pas, Marcus Gualtieri, Kate Saenko et al.

Deep RL-based socially aware motion planning enables autonomous robots to navigate safely and naturally among pedestrians, respecting social norms like passing on the right.

Yu Fan Chen, Michael Everett, Miao Liu et al.

Gaussian Process-based multiresolution mapping combined with informative path planning reduces agricultural monitoring error by 45%.

Marija Popovic, Teresa Vidal-Calleja, Gregory Hitz et al.

Proposes distributed pose graph optimization (DGS, SOR, JOR) with object models, reducing communication by over 90%.

Siddharth Choudhary, Luca Carlone, Carlos Nieto et al.

Voxblox system incrementally converts TSDF to ESDF for real-time UAV path planning, achieving 20x faster updates with <0.1m error.

Helen Oleynikova, Zachary Taylor, Marius Fehr et al.

Uses 3D CNN trained on 440,000+ models for fast shape completion, boosting robotic grasping success to 93.33%.

Jacob Varley, Chad DeChant, Adam Richardson et al.

Proposes an autonomous robot system using RGBD-based implicit mapping and active learning for dense clutter sorting, achieving over 85% success and 80% classification accuracy.

Janne V. Kujala, Tuomas J. Lukka, Harri Holopainen

Proposes a method for learning a grasp function under gripper pose uncertainty, enhancing grasp robustness.

Edward Johns, Stefan Leutenegger, Andrew J. Davison

Extended LTLvis integrates sketch-based path customization with LTL planning, enabling intuitive user interaction and real-time path synthesis.

Wei Wei, Kangjin Kim, Georgios Fainekos

This survey formalizes SLAM as MAP factor-graph optimization and defines a robust-perception agenda beyond geometric accuracy.

Cesar Cadena, Luca Carlone, Henry Carrillo et al.

Numerical optimal control with direct multiple shooting enables versatile, real-time trajectory generation for complex quadrotor systems.

Mathieu Geisert, Nicolas Mansard

Proposes incremental sparse Gaussian process regression for continuous-time trajectory estimation, achieving 3x speedup while maintaining accuracy.

Xinyan Yan, Vadim Indelman, Byron Boots