arXiv_RO
-
IndoorBEV: A Lightweight Real-Time LiDAR BEV Perception System for Indoor Mobile Robots
Abstract
Efficient indoor LiDAR perception is challenging because mobile robots must understand cluttered three-dimensional environments under strict latency and memory constraints. Existing point-based and voxel-based methods often incur substantial computational overhead, whereas conventional bird's-eye-view (BEV) representations improve efficiency at the cost of discarding vertical geometric information. We present IndoorBEV, a lightweight LiDAR perception framework that mitigates this tradeoff through a height-aware BEV representation and geometry-conditioned feature fusion. IndoorBEV summarizes the vertical point distribution in each BEV cell using statistical height features and multi-frequency height encoding, allowing informative three-dimensional cues to be processed efficiently by two-dimensional convolutions. A lightweight encoder then integrates complementary geometric features with multi-scale local representations and compact global scene context. Decoupled dense prediction heads jointly produce semantic BEV maps and oriented object bounding boxes. IndoorBEV contains only 0.6M parameters and requires 2.3 MB of model storage. On an NVIDIA AGX Orin, it uses 21.52 MB of GPU memory per inference and achieves a mean latency of 169.6 ms under a 200 ms perception deadline, with a deadline miss ratio of 1.8\%. Evaluations on simulated scenes, real-world robot scans, and an open-source indoor point-cloud dataset demonstrate a favorable tradeoff among perception accuracy, latency, and memory consumption. These results indicate that explicitly encoding vertical geometry within a compact BEV representation provides an effective approach to resource-efficient indoor LiDAR perception.
Abstract (translated)
URL
https://arxiv.org/abs/2610.00355
PDF
-
Yggdrasil: a Layer-First 3D Scene Graph for Real-Time Querying
2026-09-29 22:59:38Arshia Akhavan, Ermanno Bartoli, Afnan Algharbi, Alireza Hoseinpur, Iolanda Leite, Bryan DonyanavardAbstract
Robotic agents use 3D scene graphs (3DSG) to perform tasks ranging from scene understanding to scene interaction. Although an extensive body of work addresses scene graph generation, little attention has been paid to optimizing the graph for consumption, which leaves state-of-the-art perception pipelines to work around their own scene graph and to pay a latency cost that does not fit the real-time budget a perception loop runs on. We present Yggdrasil, the first 3D scene graph designed to be efficient for both generation and consumption: a layer-first hierarchical graph built from generic nodes, edges, and layers, which expresses the representations existing pipelines already produce, indoor or outdoor, flat or hierarchical, while natively answering the positional and semantic queries downstream tasks issue. Against a published DSG baseline, Yggdrasil answers queries up to $121\times$ faster, and every query we measure falls between 2 and 127 microseconds, three to five orders of magnitude inside the 200 microsecond keyframe budget a 3DSG consumer lives in, on both a workstation and embedded class device. We integrate Yggdrasil into three published pipelines spanning human trajectory prediction, object-goal navigation, and human-aware motion planning, where it removes up to 99% of the time each spends on its scene graph. The implementation, benchmark harness, and all three integrations are available online.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38640
PDF
-
Dense Temporal Motion Retargeting for Legged Robots
2026-09-29 22:21:54Jaeryeong Kim, Taerim Yoon, Jin Cheng, Sungjoon Choi, Stelian CorosAbstract
Legged robots can learn expressive whole-body skills from the motions of humans and animals. Due to the morphology gap between the source and the robot, however, the motion must be tailored to the dynamic properties of the robot. In particular, dynamic motions such as a jump require careful adjustment, since their timing and control are interdependent. We propose dense temporal motion retargeting (DTMR), which jointly optimizes timing and control within a single optimization, where dense means that the timing is adjusted for every control step. This dense formulation enables DTMR to deform only the parts of the motion that need a change in timing. The problem is solved with sampling-based model predictive control (MPC) in parallel on a GPU. We evaluate DTMR against baselines on two hours of human motion with four humanoid robots, where the results show that DTMR outperforms baseline methods, particularly on dynamic motions. We also show that allowing more temporal deformation yields more precise retargeting. We further compare DTMR with a baseline that optimizes the temporal dimension, where the result shows that DTMR retargets more precisely under the same deformation budget while being ~19x faster. Lastly, policies trained on our references transfer to a real humanoid robot.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38617
PDF
-
FAST-Sync: Fast Group Synchronization for any Matrix Lie Group
2026-09-29 21:55:11Shane Holmes, Yiran Luo, Firat Taxpulat, David M. Rosen, Frank DellaertAbstract
Group synchronization (GS) is the problem of estimating a set of $N$ unknown elements $g_1,\ldots, g_N \in \mathcal{G}$ in a group $\mathcal{G}$, given noisy measurements of a subset of their pairwise ratios $g_i^{-1} g_j$. GS problems lie at the core of many state estimation tasks in robotics and computer vision, including 3D vision, robotic mapping, inertial navigation, and molecular reconstruction. Unfortunately, GS problems are typically both high-dimensional and non-convex, and therefore hard to solve in general. In this paper, we present Fast-Sync, a fast linear approximation method for GS that is suitable for initializing local manifold-based optimizers or certifiable global methods. Our approach generalizes chordal initialization to arbitrary matrix Lie groups, and additionally proposes two new key algorithmic enhancements: we show how to exploit both the Kronecker-product structure in the problem data matrix and the topology of the synchronization graph to improve speed, scalability, and accuracy. Experimental evaluation across several GS tasks demonstrates that Fast-Sync provides high-quality initializations that enable local optimizers to efficiently recover globally optimal GS solutions, achieving high success rates even with considerable measurement noise.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38594
PDF
-
Drone Soccer: Learning to Manipulate with Multicopter Downwash
2026-09-29 21:47:17Neelay Joglekar, Bavin Saravanan, Yutong Wang, Varun Kandiyappan, Junyi Geng, Sebastian SchererAbstract
Although multicopter drones are traditionally designed for "perception-only" tasks, like mapping and exploration, recent work has sought to develop Unmanned Aerial Manipulators (UAMs) to solve mobile manipulation tasks. Aerial manipulation performance can be impacted by "downwash," the airflow produced by propellers, but current state-of-the-art UAMs either ignore downwash or treat it as a disturbance. Instead, is it possible to actively use downwash as a tool during manipulation? We design a drone soccer task to explore the feasibility of downwash-based manipulation. Specifically, we develop a simplified downwash dynamics model which we use to train an RL policy to dribble a soccer ball. We further demonstrate that our policy transfers to real world deployment. This work provides key insights into novel manipulation capabilities for multicopters.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38588
PDF
-
Data-Efficient Adaptation of a Driving VLA to Class 8 Trucks
2026-09-29 21:28:32Satyajeet Das, Aaron Buxbaum, Niels Joubert, Gaurav S. SukhatmeAbstract
Class 8 trucks differ from passenger cars in geometry, dynamics, and maneuvering requirements. As a result, vision-language-action (VLA) models trained for passenger vehicles do not readily transfer to Class 8 trucks, particularly in unstructured scenarios such as accident scenes and construction zones. Rather than training a truck-driving VLA from scratch, we propose an adapt-then-steer strategy that adapts an off-the-shelf VLA to generate trajectories for Class-8 trucks in these challenging scenarios. In the adapt stage, we use NVIDIA's Alpamayo 1.5 as the base model, fine-tuning only its action-generation stack on a few hundred real-world construction and accident-related highway scenarios. In the steer stage, we introduce Flow Velocity Steering (FVS) to further refine the model's predictions while holding the adapted VLA fixed. FVS is a compact, flow-time-conditioned residual module that adds learned corrections to the action-space flow velocity used to update the action sequence at each generation step. In open-loop evaluation on a scenario-disjoint held-out set, targeted fine-tuning more than halves single-candidate average displacement error (ADE) and final displacement error (FDE) over the entire 6.4 s horizon compared to the base model. Using the same targeted demonstrations, FVS further reduces the fine-tuned model's full-horizon ADE and FDE by 13.9% and 16.5%, respectively. At matched data budgets, targeted supervision yields 19-26% lower full-horizon ADE than general truck-driving supervision, while the targeted model remains competitive with a model fine-tuned on approximately 65 times as many general truck-driving scenarios. These results support adapt-then-steer for data-efficient vehicle-domain transfer to Class 8 trucks. Our project website is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38570
PDF
-
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
2026-09-29 20:54:47Galbot Team, Xuchuan Chen, Xiaoqian Cheng, Yu Deng, Lihe Ding, Shaocong Dong, Xiangjun Gao, Haozhe Jia, Zekai Li, Zhoujian Li, Yunrui Lian, Sikai Liang, Chenghuai Lin, Dairu Liu, Jiahang Liu, Qingtao Liu, Yuxuan Ma, Zekun Qi, Jiayi Su, He Wang, Ruochen Xu, Tianyu Xu, Xudong Xu, Zhe Xu, Mi Yan, Siming Yan, Li Yi, Ruixi Yu, Jinlu Zhang, Yintianrun Zhang, Zhikai Zhang, Zhizheng Zhang, Yixin Zheng, Weiyi ZhuAbstract
GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabilities as general-purpose embodied policies, we conduct comprehensive evaluations across six domains, examining direct control, cooperation with learned policies, and feedback-driven adaptation. In gripper manipulation, Astra can correct task targets and prepare contact conditions for subsequent policy execution; hybrid control with {\pi}0.5 achieves 48% success on the evaluated RoboDojo subset. In dexterous manipulation, hybrid control achieves 50% success in ten experience-guided DexJoCo trials, while direct in-hand control struggles to coordinate finger contacts. In mobile manipulation, hybrid control reaches 38.7% success on the evaluated RoboCasa365. In navigation, Astra leads our local comparisons, reaching 92% success on RxR instruction following and 82% on HM3D object search, although search incurs substantial detours. In locomotion, dense motion-reference generation remains unreliable: none of five sequential attempts on a single obstacle course reaches the goal, despite improvements in stability and forward progress. In humanoid loco-manipulation, Astra exceeds baseline methods on 13 of 30 HumanoidBench tasks with pretrained whole-body controllers. These findings reveal a gap between useful task decisions and reliable physical control. Inference latency further constrains practical control: across 50 RoboDojo instances per condition, policy-assisted and direct control consume 624.8 million and 1.132 billion tokens. A 30-second locomotion run requires 250 model calls averaging 39.86 seconds each, with physics paused during inference.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38537
PDF
-
Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics
2026-09-29 20:45:47Fernando Montes-Gonzalez (Universidad Veracruzana, Mexico)Abstract
This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the network weights. Two e-puck-type robots, controlled by a GRU network with residual connection, were evaluated in a food-seeking task with social signaling. The sensory and motor translation layer required three corrections for stable physical operation, including the calibration of a hunger term based on a measurable asymmetry in the trained residual weights. Even with these corrections, the transfer was partial and asymmetric: one agent reached the food source in one of thirty tested seeds, while the other did not reach it in any. Task success was measured by both agents reaching the food area. An additional experiment incorporating explicit directional information in the social channel produced observable changes in the trajectory of the receiving agent and improvements in several specific cases. However, these improvements were not enough to allow the second agent to reach the food source, suggesting that the limitation may not be explained solely by signal translation, but also by the ability to navigate under the new physical constraints. The results suggest that successful transfer of emergent communication may depend not only on preserving the signaling process itself, but also on preserving the ecological and navigational conditions under which the protocol evolved.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38527
PDF
-
Onboard Vision and MPC Navigation for Underwater Robots: An Open BlueROV2 Platform for Multi-Robot Experiments & Docking
2026-09-29 20:33:23Victor Nan Fernandez-Ayala, Wiktor Kowalczyk, Cezary Banaszek, Dimos V. DimarogonasAbstract
Autonomous underwater robots require robust perception, estimation and control to operate in confined environments. This paper presents an open-source BlueROV2 platform combining onboard vision with nonlinear Model Predictive Control (NMPC) for autonomous navigation and docking. The platform integrates an NVIDIA Jetson Orin NX and an Intel RealSense D435i stereo camera in a modular pressure housing. Underwater-calibrated stereo depth and realtime object detection provide relative position measurements of nearby BlueROV2 vehicles in the camera and body frames. A quaternion-based estimator fuses external pose and inertial measurements, while an NMPC controller based on a nonlinear six-degree-of-freedom model tracks planned navigation and docking trajectories. To support reproducible development, we also provide open-source physics-based PX4 SITL and Gazebo environments, multi-robot simulation tools and a lowcost physical docking station. Experiments evaluate underwater perception, onboard computational performance, state estimation, trajectory tracking and autonomous docking.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38511
PDF
-
CADeT: Causal-Aware Deformation Transmission for Indirect Robotic Manipulation of Soft Tissue
Abstract
Indirect manipulation of deep-seated deformable anatomy inaccessible to the robot is challenging in robot-assisted minimally invasive surgery (RAMIS) because intervening tissues spatially filter deformation transmission. Passive observations can be ambiguous because the Decoupled and Blocked modes may produce similar motion responses. We propose CADeT, a causal-aware deformation transmission framework that integrates structural causal model (SCM) with active sensing to infer a latent transmission mode and estimate a state-dependent adhesion Jacobian online. During normal manipulation, control actions update the mode belief; when ambiguity persists, an additional probing action is selected to improve mode distinguishability. The mode belief and learned Jacobian are incorporated into a belief-aware model predictive controller for indirect target-shape control. Validation in simulation and on the da Vinci research kit (dVRK), using phantom and ex vivo porcine tissues, shows higher mode-identification accuracy and faster shape-error convergence than the evaluated model-free and model-based baselines. These results show that active sensing improves mode identification and indirect deformation control under the evaluated conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38483
PDF
-
Diffusion-2BC: Hybrid Diffusion and Regression Training for Offline Behavior Cloning in Autonomous Driving
2026-09-29 20:04:16Bruno Maciel Machado, Eric Aislan AntoneloAbstract
Behavior cloning provides an offline route to autonomous-driving policy learning, but mean-squared-error regression is poorly matched to demonstrations in which one observation admits several valid actions. Diffusion policies can represent conditional multimodal action distributions, yet their closed-loop performance may be unstable when visual features and control are learned from limited data. This paper presents Diffusion-2BC, which combines a diffusion denoising objective with an auxiliary deterministic behavior-cloning loss over a shared visual encoder. The auxiliary branch is used only during training; inference remains diffusion-based. The proposed method is evaluated in the controlled Claw environment and in bird's-eye-view CARLA navigation, including route-conditioned driving, route-free navigation through multiple intersections, and cross-map evaluation from Town01 to Town02. In the Claw task, Diffusion-2BC reduced the mean mask-distance error by approximately 10% relative to a diffusion-based behavior-cloning baseline and by 85% relative to standard deterministic behavior cloning. In route-free CARLA, Diffusion-2BC traveled substantially farther before termination under the evaluation protocol than both baselines in Town01 and Town02. Additional qualitative rollouts revealed distinct route choices, showing the multimodal behavior of the proposed diffusion-based agent. The results indicate that an auxiliary regression signal can improve the closed-loop reliability of diffusion behavior cloning while preserving multimodal prediction in the controlled benchmark.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38472
PDF
-
L1-MPPI: L1 Adaptive Model Predictive Path Integral for Agile UAV Control
2026-09-29 19:59:05Luk\'a\v{s} Kotek, Ond\v{r}ej Proch\'azka, Vojt\v{e}ch Von\'asek, Martin Saska, Robert P\v{e}ni\v{c}kaAbstract
This work proposes the L1 Adaptive Model Predictive Path Integral (L1-MPPI). It cascades L1 adaptive control with the Model Predictive Path Integral (MPPI) to improve tracking of high-speed UAV trajectories. Thanks to the L1augmentation, the tracking remains accurate even under model uncertainties and external disturbances, such as an additional payload or a mismatch in the modeled aerodynamic drag. In contrast to existing MPPI approaches for UAV control that do not explicitly model aerodynamic effects, varying payloads, and typically neglect the dynamics of low-level motor controllers, our L1-MPPI approach enhances the dynamic model used in the MPPI by incorporating the low-level flight controller and motor dynamics, as well as an iterative mixing scheme that reflects the approach of the low-level controller. The proposed method demonstrates improved tracking performance in both simulation and the real world, even when the UAV is subjected to an unknown payload. In flight with 35% mass increase, our approach lowers the RMSE by 58.61% with respect to plain MPPI. Compared to the same MPPI using an online mass estimator in place of the L1 augmentation, the RMSE is lower by 38.59%. During the real-world experiments the UAV reaches speeds up to 13.50 m/s and accelerations up to 2.5 g.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38467
PDF
-
Observability Analysis and Online Calibration of Visual-Inertial-Wheel Odometry for 4WIS4WID Mobile Robots
2026-09-29 19:50:21Branimir \'Caran, Vladimir Mili\'c, Bojan \v{S}ekoranja, Bojan Jerbi\'cAbstract
In this paper, we present a visual-inertial-wheel odometry (VIWO) framework with online calibration for four-wheel independently steered and driven (4WIS4WID) mobile robots. We derive a 2D odometry model directly from the four driving velocities and steering angles, using both the longitudinal rolling constraints and the lateral no-slip constraints of all wheels. A preintegration model and analytical Jacobians are developed for efficient filtering and calibration. An observability analysis of the linearized VIWO system shows that a drive-only model makes all steering offsets unobservable, whereas the proposed redundant model restores their observability. The analysis also identifies four standard VINS unobservable directions and three additional directions associated with the arbitrary placement of the odometry reference frame. Furthermore, we characterize several degenerate motions, including zero yaw rate, constant steering, and a non-rolling wheel, and derive the corresponding excitation conditions for the thirteen wheel intrinsics that remain after fixing the odometry frame reference. The performance of the proposed system has been demonstrated in both simulation and real-world experiments on a 4WIS4WID mobile robot.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38462
PDF
-
Embodiment-aware control by inference over the operator: a simulation study
Abstract
Teleoperation systems are tuned for channel fidelity, while whether the operator experiences the device as part of the body, the Sense of Embodiment (SoE), is measured only afterwards, by questionnaire. Predictive-processing accounts suggest controlling devices to reduce the mismatch between the operator's predictions and the returned feedback, but those predictions are unobservable, and an objective that only penalizes mismatch is minimized by removing feedback. We formulate an embodiment-aware controller, the Universal Embodiment Engine (UEE), that infers the operator's embodiment and visuo-proprioceptive cue weighting from implicit gaze and pupil signals and task outcome, and chooses bounded device settings under explicit preferences, cast as a discrete Active Inference agent. In simulations with 300 heterogeneous synthetic operators, the UEE found the suitable setting within half a minute for most operators, before identifying their exact type, and came close to an oracle in the second half of the session (embodiment 1.68 against 0.73 for the best fixed setting, on a 0-2 scale). Adapting without reading the operator did no better than fixed control, and model-free bandits did worse, whereas an expected-utility controller with the same inference did exactly as well: the benefit comes from Bayesian inference over the operator with explicit preferences, not from the information-seeking term of Active Inference. A naive prediction-error minimizer withheld feedback, as its objective implies, and lost task success (0.74 vs 0.90). The benefit shrank but persisted for operators outside the controller's model family, grew with the variety of the population, and vanished when the controller trusted an uninformative signal or when cue weighting changed mid-session without being modeled. These failures show what studies with people must establish first: calibrated signals and a model of change.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38437
PDF
-
A Reachability-based Safety Certificate for Dynamical System Motion Policies
Abstract
Dynamical Systems (DS) are reactive motion policies representing vector fields trained with theoretical guarantees of stability and convergence. To ensure safety during deployment in unknown environments they must be locally reshaped, either through modulation or geometric control barrier function strategies. However, depending on the geometry of the obstacles and the complexity of the DS, these local strategies can lead the system to unavoidable collisions or spurious attractors. In this work, we certify safety with a value function drawn from the notion of backward reachability tube, which measures the worst-case safety along a rollout trajectory of the nominal DS. Usually, such a value function is intractable for a controlled system due to curse of dimensionality. We show that in the DS-based learning-from-demonstration setting, the absence of a control input collapses the reachability problem to a deterministic rollout, and the presence of certain stability conditions truncates the infinite horizon to a finite one, resulting in a well-defined value function. We further show that the value function we devised is the maximal forward-invariant subset of the obstaclefree region for the nominal DS flow. The application of this certificate function is validated across five DS constructions - analytical, Neural ODE, diffeomorphic latent space, LPV-DS, SE(3)and validate it on a Franka manipulator. Modulation and geometric CBFs also suffer from saddle point in cases of headon approach towards an unsafe zone. We show that CBF-on-V avoids this pitfall entirely.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38421
PDF
-
PneuTac: Tactile Manipulation with Soft Pneumatic Robots via Unified MPM-Gaussian Splatting Simulation
2026-09-29 19:12:12Shaohong Zhong, Marco Pontin, Joe Watson, Perla Maiolino, Ingmar PosnerAbstract
Soft robots and tactile sensors have demonstrated great potential in delicate manipulation tasks. Soft pneumatic robots enable safe contact through compliance, and vision-based tactile sensors offer high-resolution touch perception. However, learning tactile manipulation with compliant robots has been challenging, bottlenecked by the lack of efficient simulation. Existing simulators typically model them in isolation, and exhibit large calibration gaps that are difficult to overcome efficiently. We present PneuTac, a unified framework for tactile-feedback manipulation with soft pneumatic robots. We leverage the material point method (MPM) for modelling the dynamics of the soft robot and the deformable tactile membrane, and 3D Gaussian splatting (3DGS) for rendering. Real-to-sim modelling is done with a simple vision-based method, to then train action and perception networks for efficient simulation with surrogate models. We use the framework to drive a tactile-guided pipeline to collect demonstrations in simulation. Through experiments on a custom-designed pneumatic soft finger with a tactile sensing tip, together with additional cross-device evaluations, we show that PneuTac is capable of accurately modelling soft robots with tactile sensors, and that policies trained with simulation-augmented demonstrations outperform baselines trained on the same real data on three real-world contact-rich compliant manipulation tasks, making it a practical framework for tactile manipulation on compliant hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38418
PDF
-
Draft: A Parametric Tool for Robot Design Exploration
2026-09-29 19:00:40David Nguyen, Marcelo Coelho, Sangbae KimAbstract
Robot performance is often limited by the cost of iterating on morphology and control together, since every computer-aided design (CAD) change has to be carried into a simulation-ready model before control work begins. Co-design methods attempt to close this gap, but each uses a model generator written for a single platform or lack the use of real-world data to suggest that designs are plausible. We present Draft, a parametric generation tool whose generalized engine compiles any parametric tree of serial chains into a simulation-ready MJCF model, without CAD. It allows engineers to explore design tradeoffs through easily adjustable models and evaluate how changes influence controller performance. Draft grounds the free parameters of each design using trends fitted to a survey of $114$ actuators and $49$ published robot descriptions, so that a generated robot is anchored to real-world hardware. We validate those trends wholistically by building twins of four off-the-shelf robots, whose masses agree to $1.10\times$ geometric mean fold error. Finally, we demonstrate how Draft exposes design tradeoffs by evaluating three quadrupeds through a two-stage reinforcement learning curriculum.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38405
PDF
-
Memorize, Adapt, Ignore: Diagnosing Robot Learning Mechanisms under Training Data Variation
2026-09-29 18:57:43Ke Zhang, Danica J. Sutherland, Chao LiuAbstract
Training data variation, whether through designing a domain randomization (DR) scheme in simulation or curating demonstrations for imitation learning, is a primary lever for improving the robustness of robotic manipulation policies. Yet its underlying mechanisms remain poorly understood, and practitioners typically select randomization parameters through expensive trial and error. We investigate these mechanisms through a series of case studies, randomizing object size, color, and type as well as scene lighting and linguistic prompts across settings including pick-and-place RL in ManiSkill and fine-tuning of vision-language-action (VLA) models on LIBERO and RoboTwin. We examine both model behavior and internal representations, using the empirical neural tangent kernel (NTK) as our primary diagnostic tool. We show that the NTK distinguishes a shift in the internal learning mechanism from \textit{memorizing} different situations with insufficient variation (e.g.\ learning what to do for a large cube, and what to do for a small cube) to \textit{adapting} to the situation at hand with sufficient variation. An NTK-based signal-to-noise ratio also helps distinguish when policies have learned to \emph{ignore} task-irrelevant factors (e.g.\ treating blue and red cubes identically, instead of learning a blue sub-policy and a red sub-policy). We use these diagnostics to develop practical guidance for designing DR schemes, selecting models, and detecting shortcut learning. We further compare different kinds of representations and validate our findings with real-world hardware experiments using ACT-based imitation learning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38401
PDF
-
Unified Optimality Conditions for Stochastic Optimal Control in the Rough Path and It^o Frameworks
Abstract
Stochastic differential equations (SDEs) can be studied via Itô calculus and rough path theory. For stochastic optimal control, these two frameworks give distinct Pontryagin Maximum Principle (PMP) optimality conditions with forward-backward SDEs (FBSDEs) or rough differential equations. We show that the adjoint equations of the Itô and rough PMPs are connected via the conditional expectation $p_t^{\text{Itô}}=\mathbb{E}[p_t^{\text{rough}} \mid \mathcal{F}_t]$, where $\mathcal{F}_t$ represents information available at time $t$. First, we derive a rough stochastic PMP for problems with adapted controls that does not use FBSDEs. Its proof extends the rough stochastic PMP over deterministic controls by considering stochastic needle variations. Second, we derive a unified PMP connecting the Itô and rough PMPs, using Itô-Stratonovich conversion formulas and duality identities between the forward tangent and backward adjoint SDEs. As a first application, we rederive the adjoint matching method for fine-tuning generative models. As a second application, we propose an indirect shooting method for a class of feedback problems. Overall, these results give a new conditional bridge connecting two popular frameworks for stochastic optimal control.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38395
PDF
-
Learning to Plan from Random Exploration
2026-09-29 18:38:49Deqian Kong, Guangyan Sun, Sheng Cheng, Sirui Xie, Bo Pang, Jianwen Xie, Tony Geng, Caiwen Ding, Ying Nian WuAbstract
Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without policy-improvement training? Our random-walk analysis explains what temporal relations contain: short horizons reveal geodesic geometry in the diffusion limit, while longer horizons reveal connectivity between regions before mixing removes these distinctions. We learn these relations with a conditional energy-based model that estimates temporal log-density ratios through horizon-conditioned embeddings. The model is trained on observation pairs by noise-contrastive estimation, without action or reward labels. The planner queries these learned relations at different horizons as it moves toward the goal. At test time, a separate local dynamics model predicts candidate action outcomes, and the temporal model evaluates their progress toward the goal by selecting or aggregating estimated improvements across horizons. The agent executes one action and replans with both models fixed. Experiments demonstrate long-range maze planning from random exploration using states and images. Learned score fields, embedding probes, and planned routes exhibit properties of a multiscale cognitive map. We further demonstrate egocentric navigation from random exploration and manipulation planning from suboptimal data.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38383
PDF
