Search arXiv⌕ Search

arXiv subjects

Constantinos Chamzas

Publications and source records attributed to Constantinos Chamzas.

At least 19 recordsLinked to original sources
arXiv2026

RoboMonitor: Label-Efficient Runtime Monitoring of Robot Task Execution via Predictive Representation Learning

Learned robot policies produce actions, but their outputs alone do not establish whether execution is progressing as intended. Robot execution monitoring requires identifying the current execution phase, detecting failures, and recognizing task completion from observations available during execution. Training such monitors requires annotations that are scarce in datasets collected for robot-policy learning. We present RoboMonitor, a label-efficient vision--language execution monitor that learns from these datasets before introducing monitoring supervision. We pre-train on 25 hours of multi-camera trajectories spanning 12 manipulation tasks and two robot embodiments, using action-conditioned future-feature prediction, inverse dynamics, and masked-present prediction. We then transfer the learned visual and context encoders to a causal monitor and apply temporal supervised fine-tuning (Temporal SFT), which combines supervision throughout each observation window with consistency objectives within and across overlapping windows. At deployment, RoboMonitor requires only the task instruction and camera observations. On a four-task monitoring benchmark, RoboMonitor trained with 52 labeled episodes achieves 93.1% mean phase accuracy and 85.9% macro recall over two fine-tuning seeds, exceeding Qwen3-VL and Robometer trained with the same monitoring supervision. Its phase accuracy also exceeds that of both Qwen3-VL and Robometer trained with 100 episodes. A Qwen3-VL ablation shows that Temporal SFT reduces mean spurious phase switching from 15.23% to 4.95%. In closed-loop deployment, the integrated system completes 39 of 40 simulated Toolbox Sorting trials and 35 of 40 real-world Reel Packing trials, with no false recovery triggers observed.

cs.RO↗
arXiv2026

DGT-Map: Directional Global Traversability Mapping Utilizing Multi-Task Learning for Heterogeneous Vehicles

Off-road traversability is direction-dependent and vehicle specific, yet most global maps assign a single isotropic cost to each location. Existing learned estimators are also commonly trained independently for each vehicle; this preserves vehicle-specific behavior but prevents vehicles from sharing common terrain representations. DGT-MAP addresses both limitations through a self-supervised framework that learns global, directional, and vehicle-conditioned traversability costmaps from RGB-D observations and locomotion signals. A shared multi-task backbone learns common terrain features across training vehicles while vehicle-specific prediction heads preserve platform-dependent responses. At inference, DGT-MAP produces a heading-indexed costmap that can be used by a direction-aware planner. We evaluate DGT-MAP in simulation by integrating it into a Hybrid A* navigation stack and measuring downstream task success on challenging terrains, including slopes that are traversable downhill but not uphill and a ridge obstacle that is traversable by some vehicles, but not by others. Across evaluated tasks, DGT-MAP achieves the highest or tied-highest navigation success rate when compared against geometric, binary, and learned direction-agnostic baselines.

cs.RO↗
arXiv2026

CoAd: Constant-Time Planning for Continuous Goal Manipulation with Compressed Library and Online Adaptation

In many robotic manipulation tasks, the robot repeatedly solves motion-planning problems that differ mainly in the location of the goal object and its associated obstacle, while the surrounding workspace remains fixed. Prior works have shown that leveraging experience and offline computation can accelerate repeated planning queries, but they lack guarantees of covering the continuous task space and require storing large libraries of solutions. In this work, we present COAD, a framework that provides constant-time planning over a continuous goal-parameterized task space. COAD discretizes the continuous task space into finitely many Task Coverage Regions. Instead of planning and storing solutions for every region offline, it constructs a compressed library by only solving representative root problems. Other problems are handled through fast adaptation from these root solutions. At query time, the system retrieves a root motion in constant time and adapts it to the desired goal using lightweight adaptation modules such as linear interpolation, Dynamic Movement Primitives, or simple trajectory optimization. We evaluate the framework on various manipulators and environments in simulation and the real world, showing that COAD achieves substantial compression of the motion library while maintaining high success rates and sub-millisecond-level queries, outperforming baseline methods in both efficiency and path quality. The source code is available at https://github.com/elpis-lab/CoAd.

cs.RO↗
arXiv2026

MetaPusher: Meta Learning and Planning for Nonprehensile Manipulation of Unseen Objects with Rapid Online Adaption

Manipulating previously unseen objects remains challenging, as their dynamics depend on latent physical properties, such as friction and mass distribution, that cannot be inferred from perception alone. Prior experience across objects can provide an initial estimate of unseen object dynamics, but this estimate remains uncertain and can degrade further during sim-to-real transfer. Adapting the dynamics through interaction can progressively refine the estimation, however, updating the model may invalidate the planned trajectory. Successful and efficient manipulation therefore requires both rapid dynamics adaptation and a planning strategy that can incorporate this evolution. In this work, we introduce MetaPusher, a meta-learning and adaptive planning framework for nonprehensile manipulation of unseen objects without prior object-specific interactions. A meta-learned dynamics model rapidly adapts from interactions during task execution, while an adaptive kinodynamic planner updates long-horizon plans by reusing and refining its existing search tree. This coupling enables manipulation and adaptation without a separate data collection phase. We evaluate MetaPusher on unseen objects in simulation and in sim-to-real scenarios, comparing against fine-tuning and active learning methods, MPPI-based control, and a reinforcement learning policy. It achieves lower prediction error and improves task success rate by up to 20%.

cs.RO↗
arXiv2026

STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from Images

Robots performing long-horizon visual manipulation observe high-dimensional images, but successful plans depend on action-relevant facts: what can be done now and what changes afterward. A useful planning representation should discard irrelevant visual details while preserving action applicability and effects. Classical task planners exploit this structure through symbolic operators with preconditions and effects, but obtaining such representations from raw visual experience remains challenging. We study a visual task-planning setting in which a robot receives only image transitions: the current image, executed high-level action, and the resulting image. At test time, given a start image and a goal image, the robot must produce a sequence of high-level actions that reaches the goal. To address this problem, we introduce STRIPS-WM, a framework for learning image-grounded STRIPS-style world models directly from visual transitions. STRIPS-WM first induces a finite abstract transition graph from images, then learns latent binary predicates and one grounded propositional operator per action label. The learned operators form a symbolic action model with sparse preconditions and add/delete effects. Finally, the learned predicates are distilled into a visual encoder, enabling classical planning directly from novel start and goal images. Experiments on visual rearrangement tasks show that STRIPS-WM improves image-to-plan success over the tested visual rollout, latent graph-search and latent-symbolic baselines.

cs.RO↗
arXiv2026

AURA: Asymptotically Optimal Uncertainty-Robust Replanning Algorithm for Kinodynamic Systems

Sampling-based motion planners offer a practical and scalable approach to kinodynamic motion planning, notably for high-dimensional, underactuated, or non-holonomic systems. However, these planners are typically used offline, requiring execution to begin only after the trajectory has been computed. In addition, the planned trajectory may not be accurately tracked in the presence of motion uncertainty, leading to deviations from the nominal solution. In this work, these limitations were addressed within a unified framework, \method, an asymptotically-optimal meta-planner framework that improves both path quality and tracking performance during execution. In addition to the main execution thread, this framework comprises a replanning method that continuously explores the state space and refines the trajectory during execution, and an optimization process that refines future control inputs to reduce tracking error. Together, these components enable \method to leverage asymptotically optimal planning online while improving execution accuracy under uncertainty. The proposed approach is evaluated in both simulation and real-world environments across multiple systems, demonstrating consistent improvements in trajectory quality, tracking accuracy, and overall performance compared with baseline methods.

cs.RO↗
arXiv2026

ActivePusher: Active Learning and Planning with Residual Physics for Nonprehensile Manipulation

Planning with learned dynamics models offers a promising approach toward versatile real-world manipulation, particularly in nonprehensile settings such as pushing or rolling, where accurate analytical models are difficult to obtain. However, collecting training data for learning-based methods can be costly and inefficient, as it often relies on randomly sampled interactions that are not necessarily the most informative. Furthermore, learned models tend to exhibit high uncertainty in underexplored regions of the skill space, undermining the reliability of long-horizon planning. To address these challenges, we propose ActivePusher, a novel framework that combines residual-physics modeling with uncertainty-based active learning, to focus data acquisition on the most informative skill parameters. Additionally, ActivePusher seamlessly integrates with model-based kinodynamic planners, leveraging uncertainty estimates to bias control sampling toward more reliable actions. We evaluate our approach in both simulation and real-world environments, and demonstrate that it consistently improves data efficiency and achieves higher planning success rates in comparison to baseline methods. The source code is available at https://github.com/elpis-lab/ActivePusher.

cs.RO↗
arXiv2026

Terminal Matters: Kinodynamic Planning with a Terminal Cost and Learned Uncertainty in Belief State-Cost Space

In many real-world robotic tasks, robots must generate dynamically feasible motions that reliably reach desired goals even under uncertainty. Yet existing sampling-based kinodynamic planners typically optimize accumulated trajectory costs and treat goal reaching as a feasibility check, rather than explicitly optimizing terminal-state quality, such as goal preference or goal-reaching reliability. In this work, we introduce a terminal-cost formulation for kinodynamic planning that allows terminal-state quality to be optimized alongside accumulated trajectory cost. We prove that AO-RRT, an asymptotically optimal kinodynamic planner, preserves its asymptotic optimality under this augmented objective. We further extend the formulation to belief space and prove that minimizing the Wasserstein distance between the terminal belief and the goal improves a lower bound on the probability of reaching the goal region. The resulting planner, KiTe, uses this terminal-cost objective to encode goal preferences and improve reliability under uncertainty. To support systems without analytical uncertainty models, we learn dynamics and process uncertainty directly from data and integrate the learned belief dynamics into planning. Experiments on Flappy Bird, Car Parking, and Planar Pushing show that KiTe consistently improves goal-reaching success under uncertainty. Real-world Planar Pushing experiments further demonstrate that KiTe can plan effectively with learned dynamics and uncertainty. Source code is available at https://github.com/elpis-lab/KiTe.

cs.RO↗
arXiv2026

COVER:COverage-VErified Roadmaps for Fixed-time Motion Planning in Continuous Semi-Static Environments

The ability to solve motion-planning queries within a fixed time budget is critical for deploying robotic systems in time-sensitive applications. Semi-static environments, where most of the workspace remains fixed while a subset of obstacles varies between tasks, exhibit structured variability that can be exploited to provide stronger guarantees than general-purpose planners. However, existing approaches either lack formal coverage guarantees or rely on discretizations of obstacle configurations that restrict applicability to realistic domains. This paper introduces COVER, a framework that incrementally constructs coverage-verified roadmaps for semi-static environments. COVER decomposes the arrangement space by independently partitioning the configuration space of each movable obstacle and verifies roadmap feasibility within each partition, enabling fixed-time query resolution for verified regions.We evaluate COVER on a 7-DoF manipulator performing object-picking in tabletop and shelf environments, demonstrating broader problem-space coverage and higher query success rates than prior work, particularly with obstacles of different sizes.

cs.RO↗
arXiv2026

Learning Discrete Abstractions for Visual Rearrangement Tasks Using Vision-Guided Graph Coloring

Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an ability that enables efficient problem solving in complex environments. In robotics, abstractions and hierarchical reasoning have long been central to planning, yet they are typically hand-engineered, demanding significant human effort and limiting scalability. Automating the discovery of useful abstractions directly from visual data would make planning frameworks more scalable and more applicable to real-world robotic domains. In this work, we focus on rearrangement tasks where the state is represented with raw images, and propose a method to induce discrete, graph-structured abstractions by combining structural constraints with an attention-guided visual distance. Our approach leverages the inherent bipartite structure of rearrangement problems, integrating structural constraints and visual embeddings into a unified framework. This enables the autonomous discovery of abstractions from vision alone, which can subsequently support high-level planning. We evaluate our method on two rearrangement tasks in simulation and show that it consistently identifies meaningful abstractions that facilitate effective planning and outperform existing approaches.

cs.RO↗
arXiv2025

Image-Based Roadmaps for Vision-Only Planning and Control of Robotic Manipulators

This work presents a motion planning framework for robotic manipulators that computes collision-free paths directly in image space. The generated paths can then be tracked using vision-based control, eliminating the need for an explicit robot model or proprioceptive sensing. At the core of our approach is the construction of a roadmap entirely in image space. To achieve this, we explicitly define sampling, nearest-neighbor selection, and collision checking based on visual features rather than geometric models. We first collect a set of image-space samples by moving the robot within its workspace, capturing keypoints along its body at different configurations. These samples serve as nodes in the roadmap, which we construct using either learned or predefined distance metrics. At runtime, the roadmap generates collision-free paths directly in image space, removing the need for a robot model or joint encoders. We validate our approach through an experimental study in which a robotic arm follows planned paths using an adaptive vision-based control scheme to avoid obstacles. The results show that paths generated with the learned-distance roadmap achieved 100% success in control convergence, whereas the predefined image-space distance roadmap enabled faster transient responses but had a lower success rate in convergence.

cs.RO↗
arXiv2025

Multi-layer Motion Planning with Kinodynamic and Spatio-Temporal Constraints

We propose a novel, multi-layered planning approach for computing paths that satisfy both kinodynamic and spatiotemporal constraints. Our three-part framework first establishes potential sequences to meet spatial constraints, using them to calculate a geometric lead path. This path then guides an asymptotically optimal sampling-based kinodynamic planner, which minimizes an STL-robustness cost to jointly satisfy spatiotemporal and kinodynamic constraints. In our experiments, we test our method with a velocity-controlled Ackerman-car model and demonstrate significant efficiency gains compared to prior art. Additionally, our method is able to generate complex path maneuvers, such as crossovers, something that previous methods had not demonstrated.

cs.RO↗
arXiv2024

Expansion-GRR: Efficient Generation of Smooth Global Redundancy Resolution Roadmaps

Global redundancy resolution (GRR) roadmaps is a novel concept in robotics that facilitates the mapping from task space paths to configuration space paths in a legible, predictable, and repeatable way. Such roadmaps could find widespread utility in applications such as safe teleoperation, consistent path planning, and motion primitives generation. However, previous methods to compute GRR roadmaps often necessitate a lengthy computation time and produce non-smooth paths, limiting their practical efficacy. To address this challenge, we introduce a novel method Expansion-GRR that leverages efficient configuration space projections and enables rapid generation of smooth roadmaps that satisfy the task constraints. Additionally, we propose a simple multi-seed strategy that further enhances the final quality. We conducted experiments in simulation with a 5-link planar manipulator and a Kinova arm. We were able to generate the Expansion-GRR roadmaps up to 2 orders of magnitude faster while achieving higher smoothness. We also demonstrate the utility of the GRR roadmaps in teleoperation tasks where our method outperformed prior methods and reactive IK solvers in terms of success rate and solution quality.

cs.RO↗
arXiv2023

Sampling-Based Motion Planning: A Comparative Review

Sampling-based motion planning is one of the fundamental paradigms to generate robot motions, and a cornerstone of robotics research. This comparative review provides an up-to-date guideline and reference manual for the use of sampling-based motion planning algorithms. This includes a history of motion planning, an overview about the most successful planners, and a discussion on their properties. It is also shown how planners can handle special cases and how extensions of motion planning can be accommodated. To put sampling-based motion planning into a larger context, a discussion of alternative motion generation frameworks is presented which highlights their respective differences to sampling-based motion planning. Finally, a set of sampling-based motion planners are compared on 24 challenging planning problems. This evaluation gives insights into which planners perform well in which situations and where future research would be required. This comparative review thereby provides not only a useful reference manual for researchers in the field, but also a guideline for practitioners to make informed algorithmic decisions.

cs.RO↗
arXiv2023

Meta-Policy Learning over Plan Ensembles for Robust Articulated Object Manipulation

Recent work has shown that complex manipulation skills, such as pushing or pouring, can be learned through state-of-the-art learning based techniques, such as Reinforcement Learning (RL). However, these methods often have high sample-complexity, are susceptible to domain changes, and produce unsafe motions that a robot should not perform. On the other hand, purely geometric model-based planning can produce complex behaviors that satisfy all the geometric constraints of the robot but might not be dynamically feasible for a given environment. In this work, we leverage a geometric model-based planner to build a mixture of path-policies on which a task-specific meta-policy can be learned to complete the task. In our results, we demonstrate that a successful meta-policy can be learned to push a door, while requiring little data and being robust to model uncertainty of the environment. We tested our method on a 7-DOF Franka-Emika Robot pushing a cabinet door in simulation.

cs.RO↗
arXiv2022

cMinMax: A Fast Algorithm to Find the Corners of an N-dimensional Convex Polytope

During the last years, the emerging field of Augmented & Virtual Reality (AR-VR) has seen tremendousgrowth. At the same time there is a trend to develop low cost high-quality AR systems where computing poweris in demand. Feature points are extensively used in these real-time frame-rate and 3D applications, thereforeefficient high-speed feature detectors are necessary. Corners are such special features and often are used as thefirst step in the marker alignment in Augmented Reality (AR). Corners are also used in image registration andrecognition, tracking, SLAM, robot path finding and 2D or 3D object detection and retrieval. Therefore thereis a large number of corner detection algorithms but most of them are too computationally intensive for use inreal-time applications of any complexity. Many times the border of the image is a convex polygon. For thisspecial, but quite common case, we have developed a specific algorithm, cMinMax. The proposed algorithmis faster, approximately by a factor of 5 compared to the widely used Harris Corner Detection algorithm. Inaddition is highly parallelizable. The algorithm is suitable for the fast registration of markers in augmentedreality systems and in applications where a computationally efficient real time feature detector is necessary.The algorithm can also be extended to N-dimensional polyhedrons.

cs.CV↗
arXiv2022

Learning to Retrieve Relevant Experiences for Motion Planning

Recent work has demonstrated that motion planners' performance can be significantly improved by retrieving past experiences from a database. Typically, the experience database is queried for past similar problems using a similarity function defined over the motion planning problems. However, to date, most works rely on simple hand-crafted similarity functions and fail to generalize outside their corresponding training dataset. To address this limitation, we propose (FIRE), a framework that extracts local representations of planning problems and learns a similarity function over them. To generate the training data we introduce a novel self-supervised method that identifies similar and dissimilar pairs of local primitives from past solution paths. With these pairs, a Siamese network is trained with the contrastive loss and the similarity function is realized in the network's latent space. We evaluate FIRE on an 8-DOF manipulator in five categories of motion planning problems with sensed environments. Our experiments show that FIRE retrieves relevant experiences which can informatively guide sampling-based planners even in problems outside its training distribution, outperforming other baselines.

cs.RO↗
arXiv2022

MotionBenchMaker: A Tool to Generate and Benchmark Motion Planning Datasets

Recently, there has been a wealth of development in motion planning for robotic manipulation new motion planners are continuously proposed, each with their own unique strengths and weaknesses. However, evaluating new planners is challenging and researchers often create their own ad-hoc problems for benchmarking, which is time-consuming, prone to bias, and does not directly compare against other state-of-the-art planners. We present MotionBenchMaker, an open-source tool to generate benchmarking datasets for realistic robot manipulation problems. MotionBenchMaker is designed to be an extensible, easy-to-use tool that allows users to both generate datasets and benchmark them by comparing motion planning algorithms. Empirically, we show the benefit of using MotionBenchMaker as a tool to procedurally generate datasets which helps in the fair evaluation of planners. We also present a suite of 40 prefabricated datasets, with 5 different commonly used robots in 8 environments, to serve as a common ground to accelerate motion planning research.

cs.RO↗