Personal use of this material is permitted. Abstract -- Collision-resilient quadrotors have gained significant attention given their potential for operating in cluttered environments and leveraging impacts to perform agile maneuvers. However, existing designs are typically single-mode: either safeguarded by propeller guards that prevent deformation or deformable but lacking rigidity, which is crucial for stable flight in open environments. This paper introduces DART, a Dual-stiffness Aerial RoboT, that adapts its post-collision response by either engaging a locking mechanism for a rigid mode or disengaging it for a flexible mode, respectively. Comprehensive characterization tests highlight the significant difference in post-collision responses between its rigid and flexible modes, with the rigid mode offering seven times higher stiffness compared to the flexible mode. T o understand and harness the collision dynamics, we propose a novel collision response prediction model based on the linear complementarity system theory. We demonstrate the accuracy of predicting collision forces for both the rigid and flexible modes of DART . Experimental results confirm the accuracy of the model and underscore its potential to advance collision-inclusive trajectory planning in aerial robotics.

We introduce a data-driven approach to learn a generalized kinetic collision operator directly from molecular dynamics. Unlike the conventional (e.g., Landau) models, the present operator takes an anisotropic form that accounts for a second energy transfer arising from the collective interactions between the pair of collision particles and the environment. Numerical results show that preserving the broadly overlooked anisotropic nature of the collision energy transfer is crucial for predicting the plasma kinetics with non-negligible correlations, where the Landau model shows limitations.

In this work, we augment reinforcement learning with an inference-time collision model to ensure safe and efficient container management in a waste-sorting facility with limited processing capacity. Each container has two optimal emptying volumes that trade off higher throughput against overflow risk. Conventional reinforcement learning (RL) approaches struggle under delayed rewards, sparse critical events, and high-dimensional uncertainty -- failing to consistently balance higher-volume empties with the risk of safety-limit violations. To address these challenges, we propose a hybrid method comprising: (1) a curriculum-learning pipeline that incrementally trains a PPO agent to handle delayed rewards and class imbalance, and (2) an offline pairwise collision model used at inference time to proactively avert collisions with minimal online cost. Experimental results show that our targeted inference-time collision checks significantly improve collision avoidance, reduce safety-limit violations, maintain high throughput, and scale effectively across varying container-to-PU ratios. These findings offer actionable guidelines for designing safe and efficient container-management systems in real-world facilities.

The game of table tennis is renowned for its extremely high spin rate, but most table tennis robots today struggle to handle balls with such rapid spin. To address this issue, we have contributed a series of methods, including: 1. Curriculum Reinforcement Learning (RL): This method helps the table tennis robot learn to play table tennis progressively from easy to difficult tasks. 2. Analysis of Spinning Table Tennis Ball Collisions: We have conducted a physics-based analysis to generate more realistic trajectories of spinning table tennis balls after collision. 3. Definition of Trajectory States: The definition of trajectory states aids in setting up the reward function. 4. Selection of Valid Rally Trajectories: We have introduced a valid rally trajectory selection scheme to ensure that the robot's training is not influenced by abnormal trajectories. 5. Reality-to-Simulation (Real2Sim) Transfer: This scheme is employed to validate the trained robot's ability to handle spinning balls in real-world scenarios. With Real2Sim, the deployment costs for robotic reinforcement learning can be further reduced. Moreover, the trajectory-state-based reward function is not limited to table tennis robots; it can be generalized to a wide range of cyclical tasks. To validate our robot's ability to handle spinning balls, the Real2Sim experiments were conducted. For the specific video link of the experiment, please refer to the supplementary materials.

Reinforcement learning (RL) has shown promise in creating robust policies for robotics tasks. However, contemporary RL algorithms are data-hungry, often requiring billions of environment transitions to train successful policies. This necessitates the use of fast and highly-parallelizable simulators. In addition to speed, such simulators need to model the physics of the robots and their interaction with the environment to a level acceptable for transferring policies learned in simulation to reality. We present QuadSwarm, a fast, reliable simulator for research in single and multi-robot RL for quadrotors that addresses both issues. QuadSwarm, with fast forward-dynamics propagation decoupled from rendering, is designed to be highly parallelizable such that throughput scales linearly with additional compute. It provides multiple components tailored toward multi-robot RL, including diverse training scenarios, and provides domain randomization to facilitate the development and sim2real transfer of multi-quadrotor control policies. Initial experiments suggest that QuadSwarm achieves over 48,500 simulation samples per second (SPS) on a single quadrotor and over 62,000 SPS on eight quadrotors on a 16-core CPU. The code can be found in https://github.com/Zhehui-Huang/quad-swarm-rl.

In this work, we introduce a collision model specifically tailored for the simulation of inextensible textiles. The model considers friction, contacts, and inextensibility constraints all at the same time without any decoupling. Self-collisions are modeled in a natural way that allows considering the thickness of cloth without introducing unwanted oscillations. The discretization of the equations of motion leads naturally to a sequence of quadratic problems with inequality and equality constraints. In order to solve these problems efficiently, we develop a novel active-set algorithm that takes into account past active constraints to accelerate the resolution of unresolved contacts. We put to a test the developed collision procedure with diverse scenarios involving static and dynamic friction, sharp objects, and complex-topology folding sequences. Finally, we perform an experimental validation of the collision model by comparing simulations with recordings of real textiles as given by a $\textit{Motion Capture System}$. The results are very accurate, having errors around 1 cm for DIN A2 textiles (42 x 59.4 cm) even in difficult scenarios involving fast and strong hits with a rigid object.

Low-cost autonomous Micro Aerial Vehicles (MAVs) have the potential to help humans by simplifying and speeding up complex tasks that require their interaction with the environment, such as construction, package delivery, and search and rescue. These systems, composed of single or multiple vehicles, can be endowed with passive connection mechanisms such as rigid links or cables to perform transportation and manipulation tasks. However, they are inherently complex since they are often underactuated and evolve in nonlinear manifold configuration spaces. In addition, the complexity of systems with cable-suspended load is further increased by the hybrid dynamics depending on the cables' varying tension conditions. This paper presents the first aerial transportation and manipulation simulator incorporating different payloads and passive connection mechanisms with full system dynamics, planning, and control algorithms. Furthermore, it includes a novel general model accounting for the transient hybrid dynamics for aerial systems with cable-suspended load to closely mimic real-world systems. The availability of a flexible and intuitive interface further contributes to its usability and versatility. Comparisons between simulations and real-world experiments with different vehicles' configurations show the fidelity of the simulator results with respect to real-world settings and its benefit for rapid prototyping and transitioning of aerial transportation and manipulation systems to real-world deployment.

Active sensing and planning in unknown, cluttered environments is an open challenge for robots intending to provide home service, search and rescue, narrow-passage inspection, and medical assistance. Although many active sensing methods exist, they often consider open spaces, assume known settings, or mostly do not generalize to real-world scenarios. We present the active neural sensing approach that generates the kinematically feasible viewpoint sequences for the robot manipulator with an in-hand camera to gather the minimum number of observations needed to reconstruct the underlying environment. Our framework actively collects the visual RGBD observations, aggregates them into scene representation, and performs object shape inference to avoid unnecessary robot interactions with the environment. We train our approach on synthetic data with domain randomization and demonstrate its successful execution via sim-to-real transfer in reconstructing narrow, covered, real-world cabinet environments cluttered with unknown objects. The natural cabinet scenarios impose significant challenges for robot motion and scene reconstruction due to surrounding obstacles and low ambient lighting conditions. However, despite unfavorable settings, our method exhibits high performance compared to its baselines in terms of various environment reconstruction metrics, including planning speed, the number of viewpoints, and overall scene coverage.

Probabilistic inference in many real-world problems requires graphical models with deterministic algebraic constraints between random variables (e.g., Newtonian mechanics, Pascal’s law, Ohm’s law) that are known to be problematic for many inference methods such as Monte Carlo sampling. Fortunately, when such constraintsare invertible, the model can be collapsed and the constraints eliminated through the well-known Jacobian-based change of variables. As our first contributionin this work, we show that a much broader classof algebraic constraints can be collapsed by leveraging the properties of a Dirac delta model of deterministic constraints. Unfortunately, the collapsing processcan lead to highly piecewise densities that pose challenges for existing probabilistic inference tools. Thus,our second contribution to address these challenges is to present a variation of Gibbs sampling that efficiently samples from these piecewise densities. The key insight to achieve this is to introduce a class of functions that (1) is sufficiently rich to approximate arbitrary models up to arbitrary precision, (2) is closed under dimension reduction (collapsing) for models with (non)linear algebraic constraints and (3) always permits one analytical integral sufficient to automatically derive closed-form conditionals for Gibbs sampling. Experiments demonstrate the proposed sampler converges at least an order of magnitude faster than existing Monte Carlo samplers.