Research Papers

arXiv:2510.01711v4 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive information. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for VLA models, designed to bridge the gap between VLM representations and robotic signals. In particular, RS-CL aligns the representations more closely with the robot's proprioceptive states by using relative distances between the states as soft supervision. Complementing the original action prediction objective, RS-CL enhances control-relevant representation learning, while being lightweight and fully compatible with standard VLA training pipelines. Our empirical results demonstrate

arXiv:2510.23057v2 Announce Type: replace Abstract: We present Seq-DeepIPC, a sequential end-to-end perception-to-control model for legged robot navigation in real-world environments. Seq-DeepIPC advances intelligent sensing for autonomous legged navigation by tightly integrating multi-modal perception (RGB-D + GNSS) with temporal fusion and control. The model jointly predicts semantic segmentation and depth estimation, giving richer spatial features for planning and control. For efficient deployment on edge devices, we use a lightweight model as the encoder, reducing computation while maintaining accuracy. Heading estimation is simplified by removing the noisy IMU and instead deriving global heading via differential analysis of sequential GNSS coordinates. We collected a larger and more diverse dataset that includes both road and grass terrains, and validated Seq-DeepIPC on a robot dog. Comparative and ablation studies show that sequential inputs improve perception and control in our

arXiv:2511.00306v2 Announce Type: replace Abstract: Sliding window factor graph optimization (SW-FGO) is widely recognized for its robustness, yet its theoretical relationship with the extended Kalman filter (EKF) remains a subject of debate. This paper establishes the sufficient conditions to bridge SW-FGO with the iterated extended Kalman filter (IEKF). We introduce recursive FGO (Re-FGO), a conceptual perspective that employs a two-stage marginalization pipeline to mathematically degenerate the factor graph optimization to the IEKF recursive update. By enforcing the Markov assumption and a single-state window, we prove the theoretical equivalence between the IEKF and Re-FGO. This degeneration is validated through simulations and real-world urban GNSS and INS tightly coupled fusion experiments. The results confirm that Re-FGO exactly reproduces IEKF estimation behavior, demonstrating that the two-stage marginalization pipeline is foundational to enforce structural consistency, thereb

arXiv:2511.10276v2 Announce Type: replace Abstract: Most existing robotic manipulation benchmarks focus on tabletop or household scenarios. While these setups have driven impressive progress, it remains unclear whether generalist VLAs that excel there can truly generalize to domains with different geometry, semantics, and workflows. We introduce RoboBenchMart, an open-source simulated benchmark targeting retail dark-store environments, where a mobile manipulator must perform complex manipulation tasks with diverse grocery items. This setting presents significant challenges, including dense object clutter and varied spatial configurations, with items positioned at different heights, depths, and in close proximity. By targeting on the retail domain, our benchmark addresses a setting with strong potential for near-term automation impact. Using generated trajectories, we model a standard, realistic fine-tuning setup for current generalist VLAs and evaluate several state-of-the-art models.

arXiv:2511.17502v3 Announce Type: replace Abstract: We introduce RynnVLA-002, a unified Vision-Language-Action (VLA) and world model. The world model leverages action and visual inputs to predict future image states, learning the underlying physics of the environment to refine action generation. Conversely, the VLA model produces subsequent actions from image observations, enhancing visual understanding and supporting the world model's image generation. The unified framework of RynnVLA-002 enables joint learning of environmental dynamics and action planning. Our experiments show that RynnVLA-002 surpasses individual VLA and world models, demonstrating their mutual enhancement. We evaluate RynnVLA-002 in both simulation and real-world robot tasks. RynnVLA-002 achieves 97.4% success rate on the LIBERO simulation benchmark without pretraining, while in real-world LeRobot experiments, its integrated world model boosts the overall success rate by 50%.

arXiv:2511.22445v2 Announce Type: replace Abstract: Imitation learning has emerged as a crucial approach for acquiring visuomotor skills from demonstrations, where designing effective observation encoders is essential for policy generalization. However, existing methods tend to struggle once test-time conditions differ from the demonstrations, such as changes in lighting, texture, viewpoint, object placement, or object identity. To address this challenge, we propose DIffusion POlicy with compLementarity Encoders (DIPOLE), a visuomotor policy that learns to fuse complementary modalities through a training-time mechanism rather than a specialized fusion architecture. A modality-wise dropout masks one branch at each training step, encouraging each modality to remain individually informative. A lightweight cross-attention layer then exchanges complementary cues between the two. This design endows DIPOLE with five core strengths: stable high performance across diverse tasks, robustness to v

arXiv:2512.00470v4 Announce Type: replace Abstract: Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling process induces substantial latency, and operating directly on raw trajectory points forces the model to spend capacity on low-level kinematics, rather than high-level multi-modal semantics. To address these limitations, we propose LAtent Planner (LAP), a framework that plans in a VAE-learned latent space that disentangles high-level intents from low-level kinematics, enabling our planner to capture rich, multi-modal driving strategies. To bridge the representational gap between the high-level semantic planning space and the vectorized scene context, we introduce an intermediate feature alignment mechanism that facilitates robust information fusion. Notably, LAP can produce high-quality plans in one single denoising step, substantially reducing computational overhead. Through extensive ev

arXiv:2512.05335v4 Announce Type: replace Abstract: We study visual domain transfer for end-to-end imitation learning in a realistic and challenging setting where target-domain data are strictly off-policy, expert-free, and scarce. We first provide a theoretical analysis showing that the target-domain imitation loss can be upper bounded by the source-domain loss plus a state-conditional latent KL divergence between source and target observation models. Guided by this result, we propose State- Conditional Adversarial Learning, an off-policy adversarial framework that aligns latent distributions conditioned on system state using a discriminator-based estimator of the conditional KL term. Experiments on visually diverse autonomous driving environments built on the BARC-CARLA simulator demonstrate that SCAL achieves robust transfer and strong sample efficiency.

arXiv:2512.06182v2 Announce Type: replace Abstract: Autonomous driving in interactive traffic scenarios remains challenging because of the mutual influence among vehicles and the inherent uncertainty of surrounding agents. Several model predictive control (MPC) formulations have been proposed to address this challenge, each adopting a different model of inter-agent interaction. While higher-fidelity interaction models enable more intelligent behavior, they incur substantially greater computational cost. Since strong interactions arise only occasionally in real traffic, a practical strategy for balancing performance and computational overhead is to invoke an appropriate controller based on situational demands. To this end, we first conduct a comparative study to assess and hierarchize the interactive capabilities of different MPC formulations. Building on this hierarchy, we then develop a neural network-based classifier for situation-aware switching among these controllers. We demonstra

arXiv:2512.09065v2 Announce Type: replace Abstract: Many indoor workspaces are quasi-static: their global geometric layout is stable, but local semantics change continually, producing repetitive geometry, dynamic clutter, and perceptual noise that defeat standard vision-based localization. We present ShelfAware, a semantic particle filter for robust global localization that treats scene semantics as statistical evidence over object categories rather than fixed quantity landmarks. ShelfAware fuses a depth likelihood with a category-centric semantic similarity and uses a precomputed bank of semantic viewpoints to perform inverse semantic proposals inside Monte Carlo Localization (MCL), yielding fast, targeted hypothesis generation on low-cost, vision-only hardware. To demonstrate perception-agnostic scalability, we evaluate ShelfAware across two domains. In a rigorously controlled mock retail environment, ShelfAware achieves a 97% global localization success rate, maintaining the highest

arXiv:2512.13356v2 Announce Type: replace Abstract: This paper proposes a reinforcement learning (RL) framework for controlling and stabilizing the Twin Rotor Aerodynamic System (TRAS) at specific pitch and azimuth angles and tracking a given trajectory. The complex dynamics and non-linear characteristics of the TRAS make it challenging to control using traditional control algorithms. However, recent developments in RL have attracted interest due to their potential applications in the control of multirotors. The Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm was used in this paper to train the RL agent. This algorithm is used for environments with continuous state and action spaces, similar to the TRAS, as it does not require a model of the system. The simulation results illustrated the effectiveness of the RL control method. Next, external disturbances in the form of wind disturbances were used to test the controller's effectiveness compared to conventional PID contro

arXiv:2512.18336v2 Announce Type: replace Abstract: This paper explores the impact of dynamic entropy tuning in Reinforcement Learning (RL) algorithms that train a stochastic policy. Its performance is compared against algorithms that train a deterministic one. Stochastic policies optimize a probability distribution over actions to maximize rewards, while deterministic policies select a single deterministic action per state. The effect of training a stochastic policy with both static entropy and dynamic entropy and then executing deterministic actions to control the quadcopter is explored. It is then compared against training a deterministic policy and executing deterministic actions. For the purpose of this research, the Soft Actor-Critic (SAC) algorithm was chosen for the stochastic algorithm while the Twin Delayed Deep Deterministic Policy Gradient (TD3) was chosen for the deterministic algorithm. The training and simulation results show the positive effect the dynamic entropy tunin

arXiv:2601.11460v2 Announce Type: replace Abstract: Learning structured task representations from human demonstrations is essential for bimanual manipulation, where action ordering, object involvement, and interaction geometry vary significantly across executions. A key challenge lies in jointly capturing the discrete semantic task structure and the temporal evolution of object-centric geometric relations in a form that supports reasoning over task progression. We introduce a semantic--geometric graph-based task representation that jointly encodes object identities, inter-object semantic relations, and per-object motion histories, via a Message Passing Neural Network (MPNN) encoder and a Transformer-based decoder. The encoder operates solely on the temporal scene graph, producing structured representations decoupled from action labels. The decoder then conditions on action-context to forecast future actions, associated objects, and object motions. This decoupling learns task-agnostic r

arXiv:2601.13574v2 Announce Type: replace Abstract: Reconstructing the three-dimensional (3D) geometry of object surfaces is essential for robot perception, yet vision-based approaches degrade under low illumination or occlusion. This limitation motivates the design of a proprioceptive membrane that conforms to the surface of interest and infers 3D geometry by reconstructing its own deformation. Conventional deformation-aware membranes typically rely on resistive, capacitive, or magneto-sensitive mechanisms, but can suffer from structural complexity, limited compliance during large-scale deformation, and susceptibility to electromagnetic interference. This work presents a soft, flexible, and stretchable proprioceptive silicone membrane based on optical waveguide sensing. The membrane integrates edge-mounted LEDs and centrally-distributed photodiodes (PDs) within a multilayer elastomeric composite. Rich deformation-dependent light-intensity signals are decoded by a data-driven model to

arXiv:2606.00552v2 Announce Type: replace-cross Abstract: Multi-robot systems (MRS) increasingly offload compute-intensive perception tasks to edge nodes to meet strict time-sensitive Quality-of-Service (QoS) constraints. However, static task orchestration on a shared edge node can severely degrade QoS due to network latency, jitter, and edge-resource contention. We present a pilot edge-centric MRS testbed using Raspberry Pi nodes to evaluate a camera-to-manipulator pipeline under three modes: local execution, static offloading, and a QoS-aware Adaptive Task Placement (ATP) controller. ATP scores candidate placements using a multi-metric cost (normalized latency, CPU utilization, and switching overhead) over two-second control windows. The closed-loop visual servoing testbed is instrumented with sub-millisecond clock synchronization, network emulation, and detailed monitoring of multiple metrics across nodes to capture realistic jitter. Experimental results under compute-stress and net