CARML uses meta-learning to avoid obstacles in 2D vehicle navigation.
problem Collision avoidance in 2D vehicle navigation.
method Model-Agnostic Meta-Learning for multi-objective reinforcement learning.
result CARML outperforms a baseline TD3 solution in obstacle avoidance.
Generative neural networks applied to 2D path planning.
problem Finding paths in static environments.
method Used generative neural networks to solve path planning as an image generation task.
result Preliminary results suggest this approach is promising.
The paper uses Bayesian Surprise to identify unexpected structures in indoor environments.
problem Identifying unexpected structures in indoor environments.
method Bayesian Surprise applied to Isovist Analysis of 2D floor plans.
result Surprise regions in indoor environments can be used to focus on important areas in LBS.
This research uses PointNets to detect 2D objects from radar data.
problem Detecting 2D objects from sparse radar data for automated driving.
method Adapting PointNets for radar data, performing 2D object classification and bounding box regression.
result Demonstrates the potential of PointNets for 2D object detection in radar data.
Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…
Assisted by neural networks, reinforcement learning agents have been able to solve increasingly complex tasks over the last years. The simulation environment in which the agents interact is an essential component in any reinforcement learning problem. The environment simulates the dynamics of the agents' world and henc…
In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning mechanism. However, their application in practice has been limited to simplistic envi…
UAVs use RL to outperform a greedy shooter in 2D engagements.
problem Optimizing UAV pursuit-evasion strategies in 2D environments.
method Reinforcement learning applied to a greedy shooter strategy in a 2D aerial engagement.
result Deep Q-learning UAV outperforms greedy shooter UAV in simulations.
A novel tracking method for dense honeybee colonies using pixel personality.
problem Tracking large numbers of densely-arranged, interacting objects in a 2D environment.
method Segmentation-based object detection followed by adaptive object recognition through visual appearance.
result Reconstructed ~46% of trajectories in 5 minutes and 71% of tracks for at least 2 minutes.
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This targeting behavior is learnt solely from downstream task-specific reward withou…
PBCS combines RL and motion planning for better exploration.
problem RL algorithms struggle with versatile exploration in complex environments.
method PBCS uses motion planning to find a good trajectory, then trains RL on a curriculum derived from it.
result PBCS outperforms state-of-the-art RL algorithms in 2D maze environments.
Paper tackles efficient navigation in constrained environments using supervised and reinforcement learning.
problem Building learning agents that efficiently navigate in obstacle-cluttered environments.
method Synergistic use of supervised learning for path prediction and reinforcement learning for path following.
result Proposed method achieves good generalization and faster learning compared to existing work.
BCAE-2D compresses 3D data from a time projection chamber at high speed.
problem Compressing high-speed, sparse 3D data from a time projection chamber.
method 2D Bicephalous Convolutional Autoencoder (BCAE-2D) approach.
result 3x speedup in compression throughput with improved reconstruction accuracy.
Fast and efficient motion planning algorithms are crucial for many state-of-the-art robotics applications such as self-driving cars. Existing motion planning methods become ineffective as their computational complexity increases exponentially with the dimensionality of the motion planning problem. To address this issue…
The paper studies how grid cell patterns emerge in neural networks.
problem Understanding how grid cells in the brain form hexagonal firing patterns.
method Training recurrent neural networks with conformal normalization of velocity inputs.
result Conformal normalization is crucial for the emergence of hexagonal grid patterns in neural networks.
Evolution of planar curves under a nonlocal geometric equation is investigated. It models the simultaneous contraction and growth of carbonate particles called ooids in geosciences. Using classical ODE results and a bijective mapping we demonstrate that the steady parameters associated with the physical environment det…
We consider the exploration problem: an agent equipped with a depth sensor must map out a previously unknown environment using as few sensor measurements as possible. We propose an approach based on supervised learning of a greedy algorithm. We provide a bound on the optimality of the greedy algorithm using submodulari…
Recent developments in deep reinforcement learning have enabled the creation of agents for solving a large variety of games given a visual input. These methods have been proven successful for 2D games, like the Atari games, or for simple tasks, like navigating in mazes. It is still an open question, how to address more…
Within the Solvency II framework the insurance industry requires a realistic modelling of the risk processes relevant for its business. Every insurance company should be capable of running a holistic risk management process to meet this challenge. For property and casualty (P&C) insurance companies the risk adequate mo…
Automatically generates curricula for reinforcement learning agents.
problem Learning in dynamic, sparse reward environments.
method Setter-solver paradigm focusing on goal validity, feasibility, and coverage.
result Demonstrated success in 2D and 3D environments with varying goals.
Randomized neural networks improve deep RL agents' generalization.
problem Deep RL agents struggle to generalize to new, semantically similar environments.
method Introduce a randomized (convolutional) neural network to perturb input observations.
result Significantly outperforms various regularization and data augmentation methods.
This paper explores a simple regularizer for reinforcement learning by proposing Generative Adversarial Self-Imitation Learning (GASIL), which encourages the agent to imitate past good trajectories via generative adversarial imitation learning framework. Instead of directly maximizing rewards, GASIL focuses on reproduc…
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential d…
HRL4IN tackles interactive navigation tasks with mobile manipulators, improving efficiency and performance.
problem Interactive Navigation tasks require mobile manipulators to perform various actions, but choosing the right part of the embodiment is inefficient.
method HRL4IN uses a hierarchical reinforcement learning architecture to handle heterogeneous phases of navigation and manipulation, selecting the appropriate part of the embodiment for each phase.
result HRL4IN significantly outperforms flat PPO and HAC in terms of task performance and energy efficiency.
Bayesian segmentation and uncertainty estimation improve 3D model accuracy for factory planning.
problem Generating accurate 3D models from outdated and incomplete 2D data.
method Bayesian neural network for point cloud segmentation and entropy-based uncertainty estimation.
result Bayesian segmentation network significantly improves model accuracy and object identification.
PHASE dataset simulates complex social interactions in physical environments.
problem Lack of datasets for evaluating physically grounded perception of complex social interactions.
method Created PHASE dataset of 2D animations with procedural generation and physics engine.
result SIMPLE model outperforms neural networks in recognizing complex social interactions.
Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents. While it is often difficult to directly define the behavior of the agents, simple communicatio…
2D CNNs approximate Korobov functions with near-optimal rates.
problem Approximating Korobov functions using 2D CNNs.
method Constructive approach for 2D CNNs with ReLU activations and fully connected layers.
result 2D CNNs achieve near-optimal approximation rates for Korobov functions.
3D object detection improved using energy-based models.
problem Accurate 3D object detection in cluttered environments from sparse LiDAR data.
method Designing a differentiable pooling operator for 3D bounding boxes integrated into a state-of-the-art 3D object detector.
result Our approach consistently outperforms the SA-SSD baseline across all 3DOD metrics on the KITTI dataset.
Improved acoustic scene classification with factorized CNN.
problem Acoustic scene classification in varying environments.
method Large-margin factorized CNN with triplet loss.
result Improved performance and better generalization on unseen data.
This research tackles balancing exploration and exploitation in deep RL for partially observable systems.
problem Balancing exploration and exploitation in deep RL for partially observable systems.
method Deployed and tested several techniques including adaptive and deterministic exploration strategies, and a modified quadratic loss function.
result Adaptive methods better approximate the trade-off between exploration and exploitation.
Proposes a model to generate 3D-aware images from 2D images.
problem Generating 3D-aware images from 2D images.
method Likelihood-based top-down model using Neural Radiance Fields and energy-based latent variables.
result Model can infer 3D object structures from 2D images and generate novel views.
Previously, we proposed a physically-inspired method to construct data points into an effective in-tree (IT) structure, in which the underlying cluster structure in the dataset is well revealed. Although there are some edges in the IT structure requiring to be removed, such undesired edges are generally distinguishable…
Derive bihamiltonian structure for rational reduction of 2D-Toda hierarchy
problem Derive bihamiltonian structure for rational reduction of 2D-Toda hierarchy
method Direct computations
result Derive local bihamiltonian structure
PHYRE benchmark tests physics learning algorithms.
problem Developing efficient algorithms for physics reasoning.
method Simple classical mechanics puzzles in a 2D environment.
result Modern algorithms perform poorly on PHYRE.
Enhances 2D face recognition with 3D features using active illumination.
problem Improving robustness of 2D face recognition to spoofing attacks and low-light conditions.
method Projecting a high spatial frequency pattern onto the face to recover 3D information and a 2D image simultaneously.
result Significantly boosts face recognition performance and dramatically improves robustness to spoofing attacks.
A novel method compresses point cloud attributes by folding them onto a 2D grid.
problem Efficiently compressing point cloud attributes for storage and transmission.
method Interpreting point clouds as 2D manifolds, folding onto a grid, and mapping attributes to the grid using optimized methods.
result The proposed folding-based approach achieves performance comparable to state-of-the-art codecs.
Paper classifies brain signals using eigenvalues for 2D and 3D educational content questions.
problem Classifying brain signals for 2D and 3D educational content questions.
method Eigenvalues of covariance matrix used as features; KNN and SVM classifiers applied.
result No significant difference in learning, memory retention, and recall between 2D and 3D educational content.
Waymo Open Dataset provides a large, diverse, and synchronized LiDAR and camera dataset for autonomous driving research.
problem Limited diversity and scale in existing self-driving datasets hinder real-world problem alignment.
method Developed a new large-scale, high-quality, diverse dataset with synchronized LiDAR and camera data.
result The dataset is 15x more diverse than the largest existing dataset based on a proposed diversity metric.
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algor…
2D tissue model predicts neurotoxicity more accurately and robustly.
problem Fast and accurate prediction of developmental neurotoxicity.
method Machine learning on 2D bio-engineered tissue models.
result 2D model outperforms 3D model in accuracy and robustness.
New method reconstructs 3D shapes from 2D images using Kendall's shape space.
problem Reconstruct 3D shapes from 2D images, especially for rare specimens.
method Kendall's shape space approach with prior information.
result More robust and plausible shapes compared to previous methods.
Geometric interpretation of 2d-4d wall-crossing formulas.
problem Understanding wall-crossing phenomena in coupled 2d-4d systems.
method Deformation theory of holomorphic pairs and relation to scattering diagrams.
result Geometric interpretation of wall-crossing formulas.
The paper establishes T-duality for 2D σ-models with H-flux.
problem T-duality for 2D σ-models with H-flux.
method Localization and graded T-duality map (graded Hori morphism).
result Establishes the most general version of T-duality for Type II String Theory.
New theorem shows embedding restrictions for manifold skeletons.
problem Embedding restrictions for triangulated manifolds.
method Proves van Kampen-Flores theorem for manifolds with specific Stiefel-Whitney classes.
result Triangulated manifolds with non-trivial Stiefel-Whitney classes cannot embed into R2d. Computes a new metric quantity Y(M) for Riemannian 2d-manifolds.
problem No simple metric quantity exists for Riemannian manifolds.
method Defines Y(M) and Y_disc(M) involving sectional curvatures and computes them for specific manifolds.
result Y(M) and Y_disc(M) differ from the Euler characteristic and can be positive or negative.
The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforce…