Learning Swing-up Maneuvers for a Suspended Aerial Manipulation Platform in a Hierarchical Control Framework

In this work, we present a novel approach to augment a model-based control method with a reinforcement learning (RL) agent and demonstrate a swing-up maneuver with a suspended aerial manipulation platform. These platforms are targeted towards a wide range of applications on construction sites involving cranes, with swing-up maneuvers allowing it to perch at a given location, inaccessible with purely the thrust force of the platform. Our proposed approach is based on a hierarchical control framework, which allows different tasks to be executed according to their assigned priorities. An RL agent is then subsequently utilized to adjust the reference set-point of the lower-priority tasks to perform the swing-up maneuver, which is confined in the nullspace of the higher-priority tasks, such as maintaining a specific orientation and position of the end-effector. Our approach is validated using extensive numerical simulation studies.

DoublyAware: Dual Planning and Policy Awareness for Temporal Difference Learning in Humanoid Locomotion

Achieving robust robot learning for humanoid locomotion is a fundamental challenge in model-based reinforcement learning (MBRL), where environmental stochasticity and randomness can hinder efficient exploration and learning stability. The environmental, so-called aleatoric, uncertainty can be amplified in high-dimensional action spaces with complex contact dynamics, and further entangled with epistemic uncertainty in the models during learning phases. In this work, we propose DoublyAware, an uncertainty-aware extension of Temporal Difference Model Predictive Control (TD-MPC) that explicitly decomposes uncertainty into two disjoint interpretable components, i.e., planning and policy uncertainties. To handle the planning uncertainty, DoublyAware employs conformal prediction to filter candidate trajectories using quantile-calibrated risk bounds, ensuring statistical consistency and robustness against stochastic dynamics. Meanwhile, policy rollouts are leveraged as structured informative priors to support the learning phase with Group-Relative Policy Constraint (GRPC) optimizers that impose a group-based adaptive trust-region in the latent action space. This principled combination enables the robot agent to prioritize high-confidence, high-reward behavior while maintaining effective, targeted exploration under uncertainty. Evaluated on the HumanoidBench locomotion suite with the Unitree 26-DoF H1-2 humanoid, DoublyAware demonstrates improved sample efficiency, accelerated convergence, and enhanced motion feasibility compared to RL baselines. Our simulation results emphasize the significance of structured uncertainty modeling for data-efficient and reliable decision-making in TD-MPC-based humanoid locomotion learning.

ReFineVLA: Reasoning-Aware Teacher-Guided Transfer Fine-Tuning

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into robotic actions. Despite their recent advancements, VLAs often overlook the explicit reasoning and only learn the functional input-action mappings, omitting these crucial logical steps for interpretability and generalization for complex, long-horizon manipulation tasks. In this work, we propose \textit{ReFineVLA}, a multimodal reasoning-aware framework that fine-tunes VLAs with teacher-guided reasons. We first augment robotic datasets with reasoning rationales generated by an expert teacher model, guiding VLA models to learn to reason about their actions. Then, we use \textit{ReFineVLA} to fine-tune pre-trained VLAs with the reasoning-enriched datasets, while maintaining their inherent generalization abilities and boosting reasoning capabilities. In addition, we conduct an attention map visualization to analyze the alignment among visual attention, linguistic prompts, and to-be-executed actions of \textit{ReFineVLA}, showcasing its ability to focus on relevant tasks and actions. Through the latter step, we explore that \textit{ReFineVLA}-trained models exhibit a meaningful attention shift towards relevant objects, highlighting the enhanced multimodal understanding and improved generalization. Evaluated across manipulation tasks, \textit{ReFineVLA} outperforms the state-of-the-art baselines. Specifically, it achieves an average increase of $5.0\%$ success rate on SimplerEnv WidowX Robot tasks, improves by an average of $8.6\%$ in variant aggregation settings, and by $1.7\%$ in visual matching settings for SimplerEnv Google Robot tasks. The source code will be publicly available.

Model Tensor Planning

Sampling-based model predictive control (MPC) offers strong performance in nonlinear and contact-rich robotic tasks, yet often suffers from poor exploration due to locally greedy sampling schemes. We propose \emph{Model Tensor Planning} (MTP), a novel sampling-based MPC framework that introduces high-entropy control trajectory generation through structured tensor sampling. By sampling over randomized multipartite graphs and interpolating control trajectories with B-splines and Akima splines, MTP ensures smooth and globally diverse control candidates. We further propose a simple $\beta$-mixing strategy that blends local exploitative and global exploratory samples within the modified Cross-Entropy Method (CEM) update, balancing control refinement and exploration. Theoretically, we show that MTP achieves asymptotic path coverage and maximum entropy in the control trajectory space in the limit of infinite tensor depth and width. Our implementation is fully vectorized using JAX and compatible with MuJoCo XLA, supporting \emph{Just-in-time} (JIT) compilation and batched rollouts for real-time control with online domain randomization. Through experiments on various challenging robotic tasks, ranging from dexterous in-hand manipulation to humanoid locomotion, we demonstrate that MTP outperforms standard MPC and evolutionary strategy baselines in task success and control robustness. Design and sensitivity ablations confirm the effectiveness of MTP tensor sampling structure, spline interpolation choices, and mixing strategy. Altogether, MTP offers a scalable framework for robust exploration in model-based planning and control.

GPU-Accelerated Motion Planning of an Underactuated Forestry Crane in Cluttered Environments

Autonomous large-scale machine operations require fast, efficient, and collision-free motion planning while addressing unique challenges such as hydraulic actuation limits and underactuated joint dynamics. This paper presents a novel two-step motion planning framework designed for an underactuated forestry crane. The first step employs GPU-accelerated stochastic optimization to rapidly compute a globally shortest collision-free path. The second step refines this path into a dynamically feasible trajectory using a trajectory optimizer that ensures compliance with system dynamics and actuation constraints. The proposed approach is benchmarked against conventional techniques, including RRT-based methods and purely optimization-based approaches. Simulation results demonstrate substantial improvements in computation speed and motion feasibility, making this method highly suitable for complex crane systems.

RoboDesign1M: A Large-scale Dataset for Robot Design Understanding

Robot design is a complex and time-consuming process that requires specialized expertise. Gaining a deeper understanding of robot design data can enable various applications, including automated design generation, retrieving example designs from text, and developing AI-powered design assistants. While recent advancements in foundation models present promising approaches to addressing these challenges, progress in this field is hindered by the lack of large-scale design datasets. In this paper, we introduce RoboDesign1M, a large-scale dataset comprising 1 million samples. Our dataset features multimodal data collected from scientific literature, covering various robotics domains. We propose a semi-automated data collection pipeline, enabling efficient and diverse data acquisition. To assess the effectiveness of RoboDesign1M, we conduct extensive experiments across multiple tasks, including design image generation, visual question answering about designs, and design image retrieval. The results demonstrate that our dataset serves as a challenging new benchmark for design understanding tasks and has the potential to advance research in this field. RoboDesign1M will be released to support further developments in AI-driven robotic design automation.

FlowMP: Learning Motion Fields for Robot Planning with Conditional Flow Matching

Prior flow matching methods in robotics have primarily learned velocity fields to morph one distribution of trajectories into another. In this work, we extend flow matching to capture second-order trajectory dynamics, incorporating acceleration effects either explicitly in the model or implicitly through the learning objective. Unlike diffusion models, which rely on a noisy forward process and iterative denoising steps, flow matching trains a continuous transformation (flow) that directly maps a simple prior distribution to the target trajectory distribution without any denoising procedure. By modeling trajectories with second-order dynamics, our approach ensures that generated robot motions are smooth and physically executable, avoiding the jerky or dynamically infeasible trajectories that first-order models might produce. We empirically demonstrate that this second-order conditional flow matching yields superior performance on motion planning benchmarks, achieving smoother trajectories and higher success rates than baseline planners. These findings highlight the advantage of learning acceleration-aware motion fields, as our method outperforms existing motion planning methods in terms of trajectory quality and planning success.

Action Tokenizer Matters in In-Context Imitation Learning

In-context imitation learning (ICIL) is a new paradigm that enables robots to generalize from demonstrations to unseen tasks without retraining. A well-structured action representation is the key to capturing demonstration information effectively, yet action tokenizer (the process of discretizing and encoding actions) remains largely unexplored in ICIL. In this work, we first systematically evaluate existing action tokenizer methods in ICIL and reveal a critical limitation: while they effectively encode action trajectories, they fail to preserve temporal smoothness, which is crucial for stable robotic execution. To address this, we propose LipVQ-VAE, a variational autoencoder that enforces the Lipschitz condition in the latent action space via weight normalization. By propagating smoothness constraints from raw action inputs to a quantized latent codebook, LipVQ-VAE generates more stable and smoother actions. When integrating into ICIL, LipVQ-VAE improves performance by more than 5.3% in high-fidelity simulators, with real-world experiments confirming its ability to produce smoother, more reliable trajectories. Code and checkpoints will be released.

Towards Autonomous Wood-Log Grasping with a Forestry Crane: Simulator and Benchmarking

Forestry machines operated in forest production environments face challenges when performing manipulation tasks, especially regarding the complicated dynamics of underactuated crane systems and the heavy weight of logs to be grasped. This study investigates the feasibility of using reinforcement learning for forestry crane manipulators in grasping and lifting heavy wood logs autonomously. We first build a simulator using Mujoco physics engine to create realistic scenarios, including modeling a forestry crane with 8 degrees of freedom from CAD data and wood logs of different sizes. We further implement a velocity controller for autonomous log grasping with deep reinforcement learning using a curriculum strategy. Utilizing our new simulator, the proposed control strategy exhibits a success rate of 96% when grasping logs of different diameters and under random initial configurations of the forestry crane. In addition, reward functions and reinforcement learning baselines are implemented to provide an open-source benchmark for the community in large-scale manipulation tasks. A video with several demonstrations can be seen at https://www.acin.tuwien.ac.at/en/d18a/

Online Trajectory Replanner for Dynamically Grasping Irregular Objects

This paper presents a new trajectory replanner for grasping irregular objects. Unlike conventional grasping tasks where the object's geometry is assumed simple, we aim to achieve a "dynamic grasp" of the irregular objects, which requires continuous adjustment during the grasping process. To effectively handle irregular objects, we propose a trajectory optimization framework that comprises two phases. Firstly, in a specified time limit of 10s, initial offline trajectories are computed for a seamless motion from an initial configuration of the robot to grasp the object and deliver it to a pre-defined target location. Secondly, fast online trajectory optimization is implemented to update robot trajectories in real-time within 100 ms. This helps to mitigate pose estimation errors from the vision system. To account for model inaccuracies, disturbances, and other non-modeled effects, trajectory tracking controllers for both the robot and the gripper are implemented to execute the optimal trajectories from the proposed framework. The intensive experimental results effectively demonstrate the performance of our trajectory planning framework in both simulation and real-world scenarios.