Search Results for author:
Found 43 papers, 13 papers with code
Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentation
Safety-critical applications like autonomous driving call for robust 3D environment perception algorithms which can withstand highly diverse and ambiguous surroundings.
CellMixer: Annotation-free Semantic Cell Segmentation of Heterogeneous Cell Populations
In recent years, several unsupervised cell segmentation methods have been presented, trying to omit the requirement of laborious pixel-level annotations for the training of a cell segmentation model.
Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design
The field of antibody-based therapeutics has grown significantly in recent years, with targeted antibodies emerging as a potentially effective approach to personalized therapies.
Multi-intention Inverse Q-learning for Interpretable Behavior Representation
In advancing the understanding of decision-making processes, Inverse Reinforcement Learning (IRL) have proven instrumental in reconstructing animal's multiple intentions amidst complex behaviors.
Brain Age Revisited: Investigating the State vs. Trait Hypotheses of EEG-derived Brain-Age Dynamics with Deep Learning
Furthermore, the brain age gap biomarker is not indicative of pathological EEG.
On the Calibration of Uncertainty Estimation in LiDAR-based Semantic Segmentation
We propose a metric to measure the confidence calibration quality of a semantic segmentation model with respect to individual classes.
Context-Conditional Navigation with a Learning-Based Terrain- and Robot-Aware Dynamics Model
Terrain properties such as friction coefficients may vary over time depending on the location of the robot.
The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation
We employ our method to learn challenging multi-object robot manipulation tasks from wrist camera observations and demonstrate superior utility for policy learning compared to other representation learning techniques.
Survey on LiDAR Perception in Adverse Weather Conditions
The active LiDAR sensor is able to create an accurate 3D representation of a scene, making it a valuable addition for environment perception for autonomous vehicles.
Imitation Learning from Nonlinear MPC via the Exact Q-Loss and its Gauss-Newton Approximation
This work presents a novel loss function for learning nonlinear Model Predictive Control policies via Imitation Learning.
Robust Tumor Detection from Coarse Annotations via Multi-Magnification Ensembles
In this work, we put the focus back on tumor localization in form of a patch-level classification task and take up the setting of so-called coarse annotations, which provide greater training supervision while remaining feasible from a clinical standpoint.
Incorporating Recurrent Reinforcement Learning into Model Predictive Control for Adaptive Control in Autonomous Driving
Model Predictive Control (MPC) is attracting tremendous attention in the autonomous driving task as a powerful control technique.
Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible Robots
The development of fast and safe approximate NMPC holds the potential to accelerate the adoption of flexible robots in industry.
On the calibration of underrepresented classes in LiDAR-based semantic segmentation
The calibration of deep learning-based perception models plays a crucial role in their reliability.
Latent Plans for Task-Agnostic Offline Reinforcement Learning
Concretely, we combine a low-level policy that learns latent skills via imitation learning and a high-level policy learned from offline reinforcement learning for skill-chaining the latent behavior priors.
Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization
To deal with unknown uncertainty sets, we further propose a novel adversarial approach to generate them based on the value function.
NeuRL: Closed-form Inverse Reinforcement Learning for Neural Decoding
However, since generally there is a strong connection between learning of subjects and their expectations on long-term rewards, we propose NeuRL, an inverse reinforcement learning approach that (1) extracts an intrinsic reward function from collected trajectories of a subject in closed form, (2) maps neural signals to this intrinsic reward to account for long-term dependencies in the behavior and (3) predicts the simulated behavior for unseen neural signals by extracting Q-values and the corresponding Boltzmann policy based on the intrinsic reward values for these unseen neural signals.
Optimizing Trajectories for Highway Driving with Offline Reinforcement Learning
Implementing an autonomous vehicle that is able to output feasible, smooth and efficient trajectories is a long-standing challenge.
Affordance Learning from Play for Sample-Efficient Policy Learning
Robots operating in human-centered environments should have the ability to understand how objects function: what can be done with each object, where this interaction may occur, and how the object is used to achieve a goal.
Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning
Accurate value estimates are important for off-policy reinforcement learning.
Robust and Data-efficient Q-learning by Composite Value-estimation
In the past few years, off-policy reinforcement learning methods have shown promising results in their application for robot control.
Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty
We propose a new formulation that addresses these limitations by also modifying the feedback signals to the controller with an RL policy and show superior performance of our approach on a contact-rich peg-insertion task under position and orientation uncertainty.
Amortized Q-learning with Model-based Action Proposals for Autonomous Driving on Highways
Well-established optimization-based methods can guarantee an optimal trajectory for a short optimization horizon, typically no longer than a few seconds.
Deep Surrogate Q-Learning for Autonomous Driving
Challenging problems of deep reinforcement learning systems with regard to the application on real systems are their adaptivity to changing environments and their efficiency w. r. t.
A Dynamic Deep Neural Network For Multimodal Clinical Data Analysis
Clinical data from electronic medical records, registries or trials provide a large source of information to apply machine learning methods in order to foster precision medicine, e. g. by finding new disease phenotypes or performing individual disease prediction.
Deep Inverse Q-learning with Constraints
In this work, we introduce a novel class of algorithms that only needs to solve the MDP underlying the demonstrated behavior once to recover the expert policy.
Deep Constrained Q-learning
We analyze the advantages of Constrained Q-learning in the tabular case and compare Constrained DQN to reward shaping and Lagrangian methods in the application of high-level decision making in autonomous driving, considering constraints for safety, keeping right and comfort.
Machine-Learning-Based Diagnostics of EEG Pathology
The results demonstrate that the proposed feature-based decoding framework can achieve accuracies on the same level as state-of-the-art deep neural networks.
Composite Q-learning: Multi-scale Q-function Decomposition and Separable Optimization
We prove that the combination of these short- and long-term predictions is a representation of the full return, leading to the Composite Q-learning algorithm.
Dynamic Interaction-Aware Scene Understanding for Reinforcement Learning in Autonomous Driving
The common pipeline in autonomous driving systems is highly modular and includes a perception component which extracts lists of surrounding objects and passes these lists to a high-level decision component.
Off-policy Multi-step Q-learning
In the past few years, off-policy reinforcement learning methods have shown promising results in their application for robot control.
Dynamic Input for Deep Reinforcement Learning in Autonomous Driving
In many real-world decision making problems, reaching an optimal decision requires taking into account a variable number of objects around the agent.
Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning
We evaluate the resulting algorithm to safely explore the dynamics of an inverted pendulum and to solve a reinforcement learning task on a cart-pole system with safety constraints.
Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
Many state-of-the-art methods use intrinsic motivation to complement the sparse extrinsic reward signal, giving the agent more opportunities to receive feedback during exploration.
Compact representations and pruning in residual networks
This criterion is based on the convergence of the neural dynamics in the last two successive layers of the residual block.
Early Seizure Detection with an Energy-Efficient Convolutional Neural Network on an Implantable Microcontroller
Most approaches for early seizure detection in the literature are, however, not optimized for implementation on ultra-low power microcontrollers required for long-term implantation.
VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control
In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks.
Acting Thoughts: Towards a Mobile Robotic Service Assistant for Users with Limited Communication Skills
As our results demonstrate, our system is capable of adapting to frequent changes in the environment and reliably completing given tasks within a reasonable amount of time.
Neural SLAM: Learning to Explore with External Memory
We present an approach for agents to learn representations of a global map from sensor data, to aid their exploration in new environments.
Reinforcement Learning (RL)
Simultaneous Localization and Mapping
A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
We carry out our discussions on the two main paradigms for learning control with deep networks: deep reinforcement learning and imitation learning.
Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments
We propose a successor feature based deep reinforcement learning algorithm that can learn to transfer knowledge from previously mastered navigation tasks to new problem instances.
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images.
Guided Self-Organization of Input-Driven Recurrent Neural Networks
We review attempts that have been made towards understanding the computational properties and mechanisms of input-driven dynamical systems like RNNs, and reservoir computing networks in particular.
