Neue Studien zu Robotik und Physical AI, jeweils mit ihrer Bedeutung für die Branche.
Extending single Unmanned Aerial Vehicles (UAVs) exploration methods to multi-UAV teams can improve coverage speed and robustness, but introduces challenges such as consistent mapping, safe navigation, and deployment strategy. In this work, we present a centralized multi-UAV exploration framework that enables the use of existing single-UAV sampling-based planners in a multi-UAV setting.
Mobile robots and vehicles carry synchronized multi-camera rigs, yet many streaming 3D foundation models are designed for monocular input, leaving efficient use of rig geometry a challenge. We present StreamRig, a freeze-and-stream framework that builds causal streaming odometry for calibrated rigs on a frozen multi-view 3D foundation model.
Preprint. The authors introduce GroundAnything, a 4B-parameter visual grounding model that uses bidirectional diffusion with blockwise denoising for parallel spatial decoding instead of sequential autoregressive token generation. Its autoregressive variant, GroundAnything-VLM, reports 72.42% across 30 grounding benchmarks, ahead of GPT-6 Astra at 71.35%. This matters for latency-sensitive robotics and interactive vision systems that need fast, precise localization.
ECHO-G ist ein als Preprint veröffentlichtes Framework zur Vollkörper-Co-Speech-Bewegungsgenerierung für humanoide Roboter. Es kombiniert frame-genaue akustische Merkmale mit token-basiertem Transkriptkontext in einem Diffusion-Transformer und erzeugt direkt Bewegungsreferenzen im Roboterkoordinatenraum. Auf einem aus BEAT2 abgeleiteten G1-Datensatz erreicht der Ansatz die besten Co-Speech-Kennzahlen und die niedrigste Inferenzzeit pro Frame; in einem Nutzerstudium mit 45 Personen wird die gemeinsame Audio-Text-Konditionierung bevorzugt.
Autonomous powder weighing is one of many bottlenecks in laboratory automation due to the complex, non-linear dynamics of heterogeneous materials. Robot chemists performing this task utilise standard tools shaped for the dexterity of human hands, whose fixed geometry sets the dynamics that the control policy needs to regulate.
Physical LiDAR attacks are often evaluated using fixed primitives and manually selected parameters, despite their strong dependence on surrounding traffic. We present TACTIC, a scene-aware framework that uses a multimodal large language model (MLLM) to coordinate state-adaptive roadside LiDAR attacks.
Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system component should be revised.
A vision-language-action (VLA) policy can finish a manipulation task while knocking over objects unrelated to it, so task success alone does not show that the policy is safe to deploy in clutter. We study how to keep a pretrained VLA policy clear of such hazards at run time without retraining it, which requires guarding more of the arm than the end effector, following the hazard as it moves, and sharing onboard compute with the policy.
Echolocating bats can navigate dark and cluttered spaces using echolocation. Over a decade ago, BatSLAM showed that a robot with a biomimetic binaural sonar can build a topological map of the environment, by recognizing places from the received acoustic signals.
Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-Language Models (VLMs) exhibit promising capabilities such as object recognition, common-sense reasoning, and contextual understanding, capabilities that align with the nuanced requirements of social robot navigation.
Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments require balancing task success with unintended contact. Runtime shields can correct individual actions, but they leave the underlying policy unchanged, so repeated disagreements may create a persistent policy-shield mismatch that blocks task progress.
We present Game-Guided Skill Discovery (GGSD), a framework that uses self-play in games to discover motor skills that are directly playable by humans. Playable skills provide a compact abstraction for controlling embodied agents through a small set of learned behaviors rather than low-level actions.
The task of 3D assembly requires translating an understanding of parts and their relationships into precise spatial arrangements. Can pretrained general-purpose agents assemble objects through visual interaction without additional assembly-specific fine-tuning?
Das Paper ist ein Preprint, der eine Multiagenten-Simulation vorstellt, in der Drohnen Verkehrsstaus an Knotenpunkten erkennen und vorhersagen, um adaptive Ampelschaltungen auszulösen. Zentrale Ergebnisse sind, dass die Leistung ab einer Drohnenzahl etwa gleich der Knotenanzahl abflacht und dass eine vorausschauende Signaladaption die Staudauer ungefähr doppelt so stark reduziert wie eine reaktive Erkennung. Die Vorhersagegenauigkeit bleibt jedoch bei maximal 55 Prozent begrenzt, was auf Verbesserungsbedarf bei den Vorläufersignalen hinweist.
Vision-Language-Action (VLA) models have shown strong promise for general-purpose robotic manipulation, yet adapting them to new tasks and domains remains inefficient: existing methods often rely on parameter tuning, incurring substantial costs and risking catastrophic forgetting of previously learned tasks. To address this, we propose \textbf{Optimus-R}, a memory-centric VLA framework that formulates robotic adaptation as explicit query-skill memory tuning.
Robot brain models integrate vision, language, and robot state to generate actions for complex manipulation tasks. Most predict fixed-length action chunks that may span multiple task phases.
Der vorliegende Preprint stellt NEUPRO vor, ein neuro-symbolisches Framework, das Sicherheitsanforderungen als symbolische Regeln formuliert und mit differenzierbarem Reasoning aus Bildern grounded. Auf dem neu veröffentlichten realen Robotik-Datensatz REASON erreicht NEUPRO über alle Aufgaben eine Sicherheitsklassifikationsgenauigkeit von 0,92 ± 0,02 und liegt damit deutlich über VLM-Baselines. Der Ansatz liefert explizite Erklärungen für Sicherheitsverletzungen und ist durch graphbasiertes Reasoning 9,1-mal schneller im Training als eine tensorbasierte Variante.
Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampling to discover new strategies, resulting in agents that allocate most of their training budget to motions in free space, away from the contacts from which manipulation skills emerge.
World action models (WAMs) are large embodied policies that jointly predict future video and the actions to execute, emitting a fixed-length action chunk per inference call. Such a policy allocates its computational budget uniformly in time, unable to execute for longer over free-space motion or to spend more inference on contact-rich manipulation, which limits the throughput a WAM can reach when served in the cloud.
Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple agents in a shared environment. Classical MAPF assumes that all static obstacles are known in advance, but real-world environments can change unexpectedly due to fallen objects, spills, or other local disturbances.
Die Studien stammen aus den Robotik-Feeds von arXiv. Solange unsere Zusammenfassung fehlt, erscheinen die ersten Zeilen des Abstracts.