arXiv subjects

Emre Ugur

Publications and source records attributed to Emre Ugur.

At least 19 recordsLinked to original sources

arXiv2026

Macro-Operator Generation and Predicate Selection for TAMP Operator Learning

Creating symbolic operators by hand is one of the main bottlenecks in deploying Task and Motion Planning systems (TAMP). Recent works show that these operators can instead be learned directly from demonstration data. Existing methods, however, typically learn each action in isolation and cannot capture the recurring multi-step structure of manipulation tasks, so the search becomes intractable on long sequential tasks. A further inefficiency arises in the symbolic state: every provided predicate is evaluated at every search node, even when it never appears in any learned operator. We present a system that addresses both problems together. Its central component is the automatic generation of macro-operators, composite actions that compress a recurring sequence of individual actions into a single planning step. Our system discovers causally linked action pairs directly from the training data, where one action produces exactly the condition that the next one requires, and turns each pair into a new operator. Alongside this, our system prunes every predicate that no learned operator references, which shrinks the symbolic state evaluated at each search node. Together, these changes shorten the effective planning horizon, and the benefit they bring grows with the length of the task. Across four TAMP domains, our method reaches up to a 4.6x planning speedup compared to the baseline method, namely Learning Operators for TAMP. More importantly, it solves a long sequential task that the baseline cannot solve. Macro-operator discovery thus not only accelerates planning but, in certain domains, determines solvability in practice.

cs.RO↗

arXiv2026

Joint Discovery of Object and Action Symbols through Effect Prediction for Robotic Manipulation Planning

To perform complex manipulation planning, autonomous robots are required to abstract continuous, high-dimensional sensorimotor interactions into discrete object and action representations. Earlier work either categorized objects based on visual appearances, which fails to distinguish objects that appear similar but behave differently, or based on effects under interaction, but was limited to predefined actions. To address these limitations, we propose a model that jointly discovers high-level manipulation primitives and object categories through a binary bottleneck layer, trained to predict multi-modal outcomes, including object motion, contact, and force feedback, from random interaction data. Building on these discovered binary representations, we leverage a discrete planning method that uses intermediate steps in the predicted effect trajectory to enable partial action executions for precise low-level control. Additionally, we evaluate our framework's generalization capabilities on novel objects by assigning object categories through comparing a small number of interaction effects with the predicted effects of learned object symbols, enabling few-shot generalization based on behavior rather than visual similarity. We conduct experiments on tabletop repositioning and stacking tasks, and confirm that our effect-driven planning approach outperforms both a state-of-the-art method and a visual-based alternative in planning precision across seen and novel objects.

cs.RO↗

arXiv2026

Trajectory Learning with Graph Representations for Social Robot Navigation

Autonomous mobile robots are expected to exhibit socially compliant navigation for minimizing pedestrian disturbance. While capturing social interactions and incorporating pedestrian motion estimations into decision-making are beneficial for compliance, prior methods fail to address both spatial and temporal characteristics present in real-world data. Reinforcement Learning offers high capability, but it requires hand-crafted reward functions that reduce social behavior to static criteria, limiting its ability to reproduce patterns that exist in real pedestrian behavior. Imitation Learning offers direct training from real-world data but lacks modeling of social interactions and suffers from error accumulation. To this end, we propose an imitation learning framework that leverages spatiotemporal dynamics for socially compliant navigation. To represent social context based on interactions, we introduce a graph-based auxiliary network that encodes crowd states by attending to pedestrians. In addition, we present a navigation module that captures temporal dynamics and mitigates error accumulations by incorporating encoded state predictions and employing a trajectory-level learning objective. Our framework outperforms established data-driven baselines on simulation and a real-world dataset across diverse social metrics.

cs.RO↗

arXiv2026

Bilevel Planning with Learned Symbolic Abstractions from Interaction Data

Intelligent agents must reason over both continuous dynamics and discrete representations to generate effective plans in complex environments. Previous studies have shown that symbolic abstractions can emerge from neural effect predictors trained with a robot's unsupervised exploration. However, these methods rely on deterministic symbolic domains, lack mechanisms to verify the generated symbolic plans, and operate only at the abstract level, often failing to capture the continuous dynamics of the environment. To overcome these limitations, we propose a bilevel neuro-symbolic framework in which learned probabilistic symbolic rules generate candidate plans rapidly at the high level, and learned continuous effect models verify these plans and perform forward search when necessary at the low level. Our experiments on multi-object manipulation tasks demonstrate that the proposed bilevel method outperforms symbolic-only approaches, reliably identifying failing plans through verification, and achieves planning performance statistically comparable to continuous forward search while resolving most problems via efficient symbolic reasoning.

cs.RO↗

arXiv2026

Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations

Generalizing skill policies to novel conditions remains a key challenge in robot learning. Imitation learning methods, while data-efficient, are largely confined to the training region and consistently fail on input data outside it, leading to unpredictable policy failures. Alternatively, transfer learning approaches offer methods for trajectory generation robust to both changes in environment and tasks, but they remain data-hungry and lack accuracy in zero-shot generalization. We address these challenges in the context of task inversion learning and propose a novel joint learning approach to achieve accurate and efficient knowledge transfer. Our method constructs a common representation of the forward and inverse tasks, and leverages auxiliary forward demonstrations from novel configurations to successfully execute the corresponding inverse tasks, without any direct supervision. We demonstrate the extrapolation capabilities of our framework through ablation studies and experiments in simulated and real-world environments that require complex manipulation skills with a diverse set of objects and tools, where we outperform diffusion-based and multimodal VAE alternatives.

cs.RO↗

arXiv2026

Neuro-Symbolic Skill Discovery for Conditional Multi-Level Planning

This paper proposes a novel learning architecture for acquiring generalizable high-level symbolic skills from a few unlabeled low-level skill trajectory demonstrations. The architecture involves neural networks for symbol discovery and low-level controller acquisition and a multi-level planning pipeline that utilizes the discovered symbols and the learned low-level controllers. The discovered action symbols are automatically interpreted using visual language models that are also responsible for generating high-level plans. While extracting high-level symbols, our model preserves the low-level information so that low-level action planning can be carried out by using gradient-based planning. To assess the efficacy of our method, we tested the high and low-level planning performance of our architecture by using simulated and real-world experiments across various tasks. The experiments have shown that our method is able to manipulate objects in unseen locations and plan and execute long-horizon tasks by using novel action sequences, even in highly cluttered environments when cued by only a few demonstrations that cover small regions of the environment.

cs.RO↗

arXiv2025

Forecasting in Offline Reinforcement Learning for Non-stationary Environments

Offline Reinforcement Learning (RL) provides a promising avenue for training policies from pre-collected datasets when gathering additional interaction data is infeasible. However, existing offline RL methods often assume stationarity or only consider synthetic perturbations at test time, assumptions that often fail in real-world scenarios characterized by abrupt, time-varying offsets. These offsets can lead to partial observability, causing agents to misperceive their true state and degrade performance. To overcome this challenge, we introduce Forecasting in Non-stationary Offline RL (FORL), a framework that unifies (i) conditional diffusion-based candidate state generation, trained without presupposing any specific pattern of future non-stationarity, and (ii) zero-shot time-series foundation models. FORL targets environments prone to unexpected, potentially non-Markovian offsets, requiring robust agent performance from the onset of each episode. Empirical evaluations on offline RL benchmarks, augmented with real-world time-series data to simulate realistic non-stationarity, demonstrate that FORL consistently improves performance compared to competitive baselines. By integrating zero-shot forecasting with the agent's experience, we aim to bridge the gap between offline RL and the complexities of real-world, non-stationary environments.

cs.LG↗

arXiv2025

Interleaved Multitask Learning with Energy Modulated Learning Progress

As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However, existing machine learning methods often does not mimic human learning where tasks are intermixed due to individual preferences and environmental conditions. Humans typically switch between tasks instead of completely mastering one task before proceeding to the next. To explore how human-like task switching can enhance learning efficiency, we propose a multi task learning architecture that alternates tasks based on task-agnostic measures such as "learning progress" and "neural computational energy expenditure". To evaluate the efficacy of our method, we run several systematic experiments by using a set of effect-prediction tasks executed by a simulated manipulator robot. The experiments show that our approach surpasses random interleaved and sequential task learning in terms of average learning accuracy. Moreover, by including energy expenditure in the task switching logic, our approach can still perform favorably while reducing neural energy expenditure.

cs.RO↗

arXiv2025

Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning

Offline Reinforcement Learning (RL) methods leverage previous experiences to learn better policies than the behavior policy used for data collection. However, they face challenges handling distribution shifts due to the lack of online interaction during training. To this end, we propose a novel method named State Reconstruction for Diffusion Policies (SRDP) that incorporates state reconstruction feature learning in the recent class of diffusion policies to address the problem of out-of-distribution (OOD) generalization. Our method promotes learning of generalizable state representation to alleviate the distribution shift caused by OOD states. To illustrate the OOD generalization and faster convergence of SRDP, we design a novel 2D Multimodal Contextual Bandit environment and realize it on a 6-DoF real-world UR10 robot, as well as in simulation, and compare its performance with prior algorithms. In particular, we show the importance of the proposed state reconstruction via ablation studies. In addition, we assess the performance of our model on standard continuous control benchmarks (D4RL), namely the navigation of an 8-DoF ant and forward locomotion of half-cheetah, hopper, and walker2d, achieving state-of-the-art results. Finally, we demonstrate that our method can achieve 167% improvement over the competing baseline on a sparse continuous control navigation task where various regions of the state space are removed from the offline RL dataset, including the region encapsulating the goal.

cs.LG↗

arXiv2025

Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning

We introduce Unsupervised Meta-Testing with Conditional Neural Processes (UMCNP), a novel hybrid few-shot meta-reinforcement learning (meta-RL) method that uniquely combines, yet distinctly separates, parameterized policy gradient-based (PPG) and task inference-based few-shot meta-RL. Tailored for settings where the reward signal is missing during meta-testing, our method increases sample efficiency without requiring additional samples in meta-training. UMCNP leverages the efficiency and scalability of Conditional Neural Processes (CNPs) to reduce the number of online interactions required in meta-testing. During meta-training, samples previously collected through PPG meta-RL are efficiently reused for learning task inference in an offline manner. UMCNP infers the latent representation of the transition dynamics model from a single test task rollout with unknown parameters. This approach allows us to generate rollouts for self-adaptation by interacting with the learned dynamics model. We demonstrate our method can adapt to an unseen test task using significantly fewer samples during meta-testing than the baselines in 2D-Point Agent and continuous control meta-RL benchmarks, namely, cartpole with unknown angle sensor bias, walker agent with randomized dynamics parameters.

cs.LG↗

arXiv2025

Predictability-Based Curiosity-Guided Action Symbol Discovery

Discovering symbolic representations for skills is essential for abstract reasoning and efficient planning in robotics. Previous neuro-symbolic robotic studies mostly focused on discovering perceptual symbolic categories given a pre-defined action repertoire and generating plans with given action symbols. A truly developmental robotic system, on the other hand, should be able to discover all the abstractions required for the planning system with minimal human intervention. In this study, we propose a novel system that is designed to discover symbolic action primitives along with perceptual symbols autonomously. Our system is based on an encoder-decoder structure that takes object and action information as input and predicts the generated effect. To efficiently explore the vast continuous action parameter space, we introduce a Curiosity-Based exploration module that selects the most informative actions -- the ones that maximize the entropy in the predicted effect distribution. The discovered symbolic action primitives are then used to make plans using a symbolic tree search strategy in single- and double-object manipulation tasks. We compare our model with two baselines that use different exploration strategies in different experiments. The results show that our approach can learn a diverse set of symbolic action primitives, which are effective for generating plans in order to achieve given manipulation goals.

cs.RO↗

arXiv2025

RAMPA: Robotic Augmented Reality for Machine Programming by DemonstrAtion

This paper introduces Robotic Augmented Reality for Machine Programming by Demonstration (RAMPA), the first ML-integrated, XR-driven end-to-end robotic system, allowing training and deployment of ML models such as ProMPs on the fly, and utilizing the capabilities of state-of-the-art and commercially available AR headsets, e.g., Meta Quest 3, to facilitate the application of Programming by Demonstration (PbD) approaches on industrial robotic arms, e.g., Universal Robots UR10. Our approach enables in-situ data recording, visualization, and fine-tuning of skill demonstrations directly within the user's physical environment. RAMPA addresses critical challenges of PbD, such as safety concerns, programming barriers, and the inefficiency of collecting demonstrations on the actual hardware. The performance of our system is evaluated against the traditional method of kinesthetic control in teaching three different robotic manipulation tasks and analyzed with quantitative metrics, measuring task performance and completion time, trajectory smoothness, system usability, user experience, and task load using standardized surveys. Our findings indicate a substantial advancement in how robotic tasks are taught and refined, promising improvements in operational safety, efficiency, and user engagement in robotic programming.

cs.RO↗

arXiv2024

Multi-Object Graph Affordance Network: Goal-Oriented Planning through Learned Compound Object Affordances

Learning object affordances is an effective tool in the field of robot learning. While the data-driven models investigate affordances of single or paired objects, there is a gap in the exploration of affordances of compound objects composed of an arbitrary number of objects. We propose the Multi-Object Graph Affordance Network which models complex compound object affordances by learning the outcomes of robot actions that facilitate interactions between an object and a compound. Given the depth images of the objects, the object features are extracted via convolution operations and encoded in the nodes of graph neural networks. Graph convolution operations are used to encode the state of the compounds, which are used as input to decoders to predict the outcome of the object-compound interactions. After learning the compound object affordances, given different tasks, the learned outcome predictors are used to plan sequences of stack actions that involve stacking objects on top of each other, inserting smaller objects into larger containers and passing through ring-like objects through poles. We showed that our system successfully modeled the affordances of compound objects that include concave and convex objects, in both simulated and real-world environments. We benchmarked our system with a baseline model to highlight its advantages.

cs.RO↗

arXiv2024

Cross-Embodied Affordance Transfer through Learning Affordance Equivalences

Affordances represent the inherent effect and action possibilities that objects offer to the agents within a given context. From a theoretical viewpoint, affordances bridge the gap between effect and action, providing a functional understanding of the connections between the actions of an agent and its environment in terms of the effects it can cause. In this study, we propose a deep neural network model that unifies objects, actions, and effects into a single latent vector in a common latent space that we call the affordance space. Using the affordance space, our system can generate effect trajectories when action and object are given and can generate action trajectories when effect trajectories and objects are given. Our model does not learn the behavior of individual objects acted upon by a single agent. Still, rather, it forms a `shared affordance representation' spanning multiple agents and objects, which we call Affordance Equivalence. Affordance Equivalence facilitates not only action generalization over objects but also Cross Embodiment transfer linking actions of different robots. In addition to the simulation experiments that demonstrate the proposed model's range of capabilities, we also showcase that our model can be used for direct imitation in real-world settings.

cs.RO↗

arXiv2024

Conditional Neural Expert Processes for Learning Movement Primitives from Demonstration

Learning from Demonstration (LfD) is a widely used technique for skill acquisition in robotics. However, demonstrations of the same skill may exhibit significant variances, or learning systems may attempt to acquire different means of the same skill simultaneously, making it challenging to encode these motions into movement primitives. To address these challenges, we propose an LfD framework, namely the Conditional Neural Expert Processes (CNEP), that learns to assign demonstrations from different modes to distinct expert networks utilizing the inherent information within the latent space to match experts with the encoded representations. CNEP does not require supervision on which mode the trajectories belong to. We compare the performance of CNEP against widely used and powerful LfD methods such as Gaussian Mixture Models, Probabilistic Movement Primitives, and Stable Movement Primitives and show that our method outperforms these baselines on multimodal trajectory datasets. The results reveal enhanced modeling performance for movement primitives, leading to the synthesis of trajectories that more accurately reflect those demonstrated by experts, particularly when the skill demonstrations include intersection points from various trajectories. We evaluated the CNEP model on two real-robot tasks, namely obstacle avoidance and pick-and-place tasks, that require the robot to learn multi-modal motion trajectories and execute the correct primitives given target environment conditions. We also showed that our system is capable of on-the-fly adaptation to environmental changes via an online conditioning mechanism. Lastly, we believe that CNEP offers improved explainability and interpretability by autonomously finding discrete behavior primitives and providing probability values about its expert selection decisions.

cs.RO↗

arXiv2024

Bidirectional Human Interactive AI Framework for Social Robot Navigation

Trustworthiness is a crucial concept in the context of human-robot interaction. Cooperative robots must be transparent regarding their decision-making process, especially when operating in a human-oriented environment. This paper presents a comprehensive end-to-end framework aimed at fostering trustworthy bidirectional human-robot interaction in collaborative environments for the social navigation of mobile robots. In this framework, the robot communicates verbally while the human guides with gestures. Our method enables a mobile robot to predict the trajectory of people and adjust its route in a socially-aware manner. In case of conflict between human and robot decisions, detected through visual examination, the route is dynamically modified based on human preference while verbal communication is maintained. We present our pipeline, framework design, and preliminary experiments that form the foundation of our proposition.

cs.RO↗

arXiv2024

Learning Early Social Maneuvers for Enhanced Social Navigation

Socially compliant navigation is an integral part of safety features in Human-Robot Interaction. Traditional approaches to mobile navigation prioritize physical aspects, such as efficiency, but social behaviors gain traction as robots appear more in daily life. Recent techniques to improve the social compliance of navigation often rely on predefined features or reward functions, introducing assumptions about social human behavior. To address this limitation, we propose a novel Learning from Demonstration (LfD) framework for social navigation that exclusively utilizes raw sensory data. Additionally, the proposed system contains mechanisms to consider the future paths of the surrounding pedestrians, acknowledging the temporal aspect of the problem. The final product is expected to reduce the anxiety of people sharing their environment with a mobile robot, helping them trust that the robot is aware of their presence and will not harm them. As the framework is currently being developed, we outline its components, present experimental results, and discuss future work towards realizing this framework.

cs.RO↗

arXiv2024

Learning Social Navigation from Demonstrations with Deep Neural Networks

Traditional path-planning techniques treat humans as obstacles. This has changed since robots started to enter human environments. On modern robots, social navigation has become an important aspect of navigation systems. To use learning-based techniques to achieve social navigation, a powerful framework that is capable of representing complex functions with as few data as possible is required. In this study, we benefited from recent advances in deep learning at both global and local planning levels to achieve human-aware navigation on a simulated robot. Two distinct deep models are trained with respective objectives: one for global planning and one for local planning. These models are then employed in the simulated robot. In the end, it has been shown that our model can successfully carry out both global and local planning tasks. We have shown that our system could generate paths that successfully reach targets while avoiding obstacles with better performance compared to feed-forward neural networks.

cs.RO↗