Author name cluster

Aleksandar Taranovic

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

Niklas Freymuth
Tobias Würth
Nicolas Schreiber
Balázs Gyenes
Andreas Boltres
Johannes Mitsch
Aleksandar Taranovic
Tai Hoang

The cost and accuracy of simulating complex physical systems using the Finite Element Method (FEM) scales with the resolution of the underlying mesh. Adaptive meshes improve computational efficiency by refining resolution in critical regions, but typically require task-specific heuristics or cumbersome manual design by a human expert. We propose Adaptive Meshing By Expert Reconstruction (AMBER), a supervised learning approach to mesh adaptation. Starting from a coarse mesh, AMBER iteratively predicts the sizing field, i. e. , a function mapping from the geometry to the local element size of the target mesh, and uses this prediction to produce a new intermediate mesh using an out-of-the-box mesh generator. This process is enabled through a hierarchical graph neural network, and relies on data augmentation by automatically projecting expert labels onto AMBER-generated data during training. We evaluate AMBER on 2D and 3D datasets, including classical physics problems, mechanical components, and real-world industrial designs with human expert meshes. AMBER generalizes to unseen geometries and consistently outperforms multiple recent baselines, including ones using Graph and Convolutional Neural Networks, and Reinforcement Learning-based approaches.

PDF Details

NeurIPS Conference 2025 Conference Paper

Scaffolding Dexterous Manipulation with Vision-Language Models

Vincent de Bakker
Joey Hejna
Tyler Lum
Onur Celik
Aleksandar Taranovic
Denis Blessing
Gerhard Neumann
Jeannette Bohg

Dexterous robotic hands are essential for performing complex manipulation tasks, yet remain difficult to train due to the challenges of demonstration collection and high-dimensional control. While reinforcement learning (RL) can alleviate the data bottleneck by generating experience in simulation, it typically relies on carefully designed, task-specific reward functions, which hinder scalability and generalization. Thus, contemporary works in dexterous manipulation have often bootstrapped from reference trajectories. These trajectories specify target hand poses that guide the exploration of RL policies and object poses that enable dense, task-agnostic rewards. However, sourcing suitable trajectories---particularly for dexterous hands---remains a significant challenge. Yet, the precise details in explicit reference trajectories are often unnecessary, as RL ultimately refines the motion. Our key insight is that modern vision-language models (VLMs) already encode the commonsense spatial and semantic knowledge needed to specify tasks and guide exploration effectively. Given a task description (e. g. , “open the cabinet”) and a visual scene, our method uses an off-the-shelf VLM to first identify task-relevant keypoints (e. g. , handles, buttons) and then synthesize 3D trajectories for hand motion and object motion. Subsequently, we train a low-level residual RL policy in simulation to track these coarse trajectories or ``scaffolds'' with high fidelity. Across a number of simulated tasks involving articulated objects and semantic understanding, we demonstrate that our method is able to learn robust dexterous manipulation policies. Moreover, we showcase that our method transfers to real-world robotic hands without any human demonstrations or handcrafted rewards.

PDF Details

ICML Conference 2024 Conference Paper

Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts

Onur Celik
Aleksandar Taranovic
Gerhard Neumann

Reinforcement learning (RL) is a powerful approach for acquiring a good-performing policy. However, learning diverse skills is challenging in RL due to the commonly used Gaussian policy parameterization. We propose Diverse Skill Learning (Di-SkilL), an RL method for learning diverse skills using Mixture of Experts, where each expert formalizes a skill as a contextual motion primitive. Di-SkilL optimizes each expert and its associate context distribution to a maximum entropy objective that incentivizes learning diverse skills in similar contexts. The per-expert context distribution enables automatic curricula learning, allowing each expert to focus on its best-performing sub-region of the context space. To overcome hard discontinuities and multi-modalities without any prior knowledge of the environment’s unknown context probability space, we leverage energy-based models to represent the per-expert context distributions and demonstrate how we can efficiently train them using the standard policy gradient objective. We show on challenging robot simulation tasks that Di-SkilL can learn diverse and performant skills.

Details

ICLR Conference 2023 Conference Paper

Adversarial Imitation Learning with Preferences

Aleksandar Taranovic
Andras G. Kupcsik
Niklas Freymuth
Gerhard Neumann

Designing an accurate and explainable reward function for many Reinforcement Learning tasks is a cumbersome and tedious process. Instead, learning policies directly from the feedback of human teachers naturally integrates human domain knowledge into the policy optimization process. However, different feedback modalities, such as demonstrations and preferences, provide distinct benefits and disadvantages. For example, demonstrations convey a lot of information about the task but are often hard or costly to obtain from real experts while preferences typically contain less information but are in most cases cheap to generate. However, existing methods centered around human feedback mostly focus on a single teaching modality, causing them to miss out on important training data while making them less intuitive to use. In this paper we propose a novel method for policy learning that incorporates two different feedback types, namely \emph{demonstrations} and \emph{preferences}. To this end, we make use of the connection between discriminator training and density ratio estimation to incorporate preferences into the popular Adversarial Imitation Learning paradigm. This insight allows us to express loss functions over both demonstrations and preferences in a unified framework. Besides expert demonstrations, we are also able to learn from imperfect ones and combine them with preferences to achieve improved task performance. We experimentally validate the effectiveness of combining both preferences and demonstrations on common benchmarks and also show that our method can efficiently learn challenging robot manipulation tasks.

Details

IROS Conference 2018 Conference Paper

Adaptive Modality Selection Algorithm in Robot-Assisted Cognitive Training

Aleksandar Taranovic
Aleksandar Jevtic
Carme Torras

Interaction of socially assistive robots with users is based on social cues coming from different interaction modalities, such as speech or gestures. However, using all modalities at all times may be inefficient as it can overload the user with redundant information and increase the task completion time. Additionally, users may favor certain modalities over the other as a result of their disability or personal preference. In this paper, we propose an Adaptive Modality Selection (AMS) algorithm that chooses modalities depending on the state of the user and the environment, as well as user preferences. The variables that describe the environment and the user state are defined as resources, and we posit that modalities are successful if certain resources possess specific values during their use. Besides the resources, the proposed algorithm takes into account user preferences which it learns while interacting with users. We tested our algorithm in simulations, and we implemented it on a robotic system that provides cognitive training, specifically Sequential memory exercises. Experimental results show that it is possible to use only a subset of available modalities without compromising the interaction. Moreover, we see a trend for users to perform better when interacting with a system with implemented AMS algorithm.

Details