arXiv subjects

Yu-Ming Chen

Publications and source records attributed to Yu-Ming Chen.

11 recordsLinked to original sources

arXiv2026

Bicycle Acrobatics with Reinforcement Learning

Bicycle robots are fast and energy efficient, but their simple mechanical design and their underactuated and non-holonomic dynamics make highly agile maneuvers difficult to achieve. Here, we use Reinforcement Learning (RL) to enable a bicycle robot to learn and compose a diverse repertoire of dynamic acrobatic stunts. Using different RL formulations such as waypoint following, pose reaching, twist tracking, guided tracking, and motion imitation, the robot acquires autonomous single and multi-table forward and lateral jumps, steerable jumps, front flips, kip-ups, kip-downs, driving, wheelies, bunny hops, and three-point turns. To coordinate these behaviors, we introduce an orchestrator that transitions between policies using state-dependent triggers, enabling robust long-horizon acrobatic stunts. We validate the approach on the Ultra Mobility Vehicle (UMV), a custom bicycle robot, in simulation and hardware. The robot repeatedly traverses tables up to 1 m high, performs more than 15 consecutive autonomous jumps while following waypoints, handles previously unseen multi-table configurations, executes continuous repertoires of kipups, jumps, flips, kip-downs, over more than 20 consecutive trials, and performs more than 10 consecutive autonomous and steerable repertoires of wheelies, lateral jumps, and single-wheel jump downs. These results demonstrate that RL can endow bicycle robots with levels of agility previously associated primarily with legged platforms while preserving the speed and efficiency of wheeled locomotion, establishing a foundation for bicycle acrobatics.

cs.RO↗

arXiv2026

System Design of the Ultra Mobility Vehicle: A Driving, Balancing, and Jumping Bicycle Robot

Trials cyclists and mountain bike riders can hop, jump, balance, and drive on one or both wheels. This versatility allows them to achieve speed and energy-efficiency on smooth terrain and agility over rough terrain. Inspired by these athletes, we present the design and control of a robotic platform, Ultra Mobility Vehicle (UMV), which combines a bicycle and a reaction mass to move dynamically with minimal actuated degrees of freedom. We employ a simulation-driven design optimization process to synthesize a spatial linkage topology with a focus on vertical jump height and momentum-based balancing on a single wheel contact. Using a constrained Reinforcement Learning (RL) framework, we demonstrate zero-shot transfer of diverse athletic behaviors, including track-stands, jumps, wheelies, rear wheel hopping, and front flips. This 23.5 kg robot is capable of high speeds (8 m/s) and jumping on and over large obstacles (1 m tall, or 130% of the robot's nominal height).

cs.RO↗

arXiv2025

Probing Light Primordial Black Holes through Non-cold Dark Matter

We study the matter power spectrum constraint on primordial black holes (PBH) by the dark matter (DM) emitted through Hawking radiation. We particularly focus on the scenario where PBH, with mass ranges between 1g and $10^9$g, evaporates before big-bang nucleosynthesis (BBN). Addition to that, we consider the case where PBH abundance is scarce and there is no early PBH domination taking place. On the DM side, we assume a fraction of the population is produced from PBH evaporation, while the remaining part is the regular cold dark matters (CDMs) which is produced by some genesis processes that decouples later on. Therefore, in the rest of the cosmological history, DM interacts solely through gravity. Under this condition, there is no thermal equilibrium ever established between DM and SM plasma. An important feature in our analysis is that, for the light PBH we consider, its temperature is much larger than the mass of DM which is consequently produced ultra-relativistically and require a protracted time to become matter-like. In this context, even though PBH evaporates in the very early Universe, PBH-produced DM could still be energetic and smooth out the small scale structure at much later time. By the precision measurement on the matter power spectrum from cosmic surveys, we are able to set joint constraint on light PBHs and the non-cold DMs it produced.

hep-ph↗

arXiv2024

BBN Constraint on Heavy Neutrino Production and Decay

We explore the big-bang nucleosynthesis (BBN) constraint on heavy neutrino that is a mixture of gauge singlet fermion and active neutrinos in the Standard Model. We work in the minimal model with only two parameters, the heavy neutrino mass $m_4$ and the mixing parameter $|U_{a4}|^2$, where $a=e$, $\mu$, or $\tau$ stands for the active neutrino flavor. We show that both the early universe production mechanism and decay products of the heavy neutrino are determined by $m_4$ and $|U_{a4}|^2$, with little room for further assumptions. This predictivity allows us to present a portrait of the entire BBN excluded parameter space. Our analysis includes various effects including temporary matter domination, energy injections in the form of charged mesons, photons and light neutrinos. The BBN constraint is complementary to terrestrial search for heavy neutrinos (heavy neutral leptons) behind the origin of neutrino masses and portal to the dark sector.

hep-ph↗

arXiv2024

Predicting Fine-grained Behavioral and Psychological Symptoms of Dementia Based on Machine Learning and Smart Wearable Devices

Behavioral and Psychological Symptoms of Dementia (BPSD) impact dementia care substantially, affecting both patients and caregivers. Effective management and early detection of BPSD are crucial to reduce the stress and burden on caregivers and healthcare systems. Despite the advancements in machine learning for dementia prediction, there is a considerable gap in utilizing these methods for BPSD prediction. This study aims to fill this gap by presenting a novel personalized framework for BPSD prediction, utilizing physiological signals from smart wearable devices. Our personalized fine-grained BPSD prediction method accurately predicts BPSD occurrences by extracting individual behavioral patterns, while the generalized models identify diverse patterns and differentiate between various BPSD symptoms. Detailed comparisons between the proposed personalized method and conventional generalized methods reveals substantial improvements across all performance metrics, including a 16.0% increase in AUC. These results demonstrate the potential of our proposed method in advancing dementia care by enabling proactive interventions and improving patient outcomes in real-world scenarios. To the best of our knowledge, this is the first study that leverages physiological signals from smart wearable devices to predict BPSD, marking a significant stride in dementia care research.

eess.SP↗

arXiv2023

Reinforcement Learning for Reduced-order Models of Legged Robots

Model-based approaches for planning and control for bipedal locomotion have a long history of success. It can provide stability and safety guarantees while being effective in accomplishing many locomotion tasks. Model-free reinforcement learning, on the other hand, has gained much popularity in recent years due to computational advancements. It can achieve high performance in specific tasks, but it lacks physical interpretability and flexibility in re-purposing the policy for a different set of tasks. For instance, we can initially train a neural network (NN) policy using velocity commands as inputs. However, to handle new task commands like desired hand or footstep locations at a desired walking velocity, we must retrain a new NN policy. In this work, we attempt to bridge the gap between these two bodies of work on a bipedal platform. We formulate a model-based reinforcement learning problem to learn a reduced-order model (ROM) within a model predictive control (MPC). Results show a 49% improvement in viable task region size and a 21% reduction in motor torque cost. All videos and code are available at https://sites.google.com/view/ymchen/research/rl-for-roms.

cs.RO↗

arXiv2023

Beyond Inverted Pendulums: Task-optimal Simple Models of Legged Locomotion

Reduced-order models (ROM) are popular in online motion planning due to their simplicity. A good ROM for control captures critical task-relevant aspects of the full dynamics while remaining low dimensional. However, planning within the reduced-order space unavoidably constrains the full model, and hence we sacrifice the full potential of the robot. In the community of legged locomotion, this has lead to a search for better model extensions, but many of these extensions require human intuition, and there has not existed a principled way of evaluating the model performance and discovering new models. In this work, we propose a model optimization algorithm that automatically synthesizes reduced-order models, optimal with respect to a user-specified distribution of tasks and corresponding cost functions. To demonstrate our work, we optimized models for a bipedal robot Cassie. We show in simulation that the optimal ROM reduces the cost of Cassie's joint torques by up to 23% and increases its walking speed by up to 54%. We also show hardware result that the real robot walks on flat ground with 10% lower torque cost. All videos and code can be found at https://sites.google.com/view/ymchen/research/optimal-rom.

cs.RO↗

arXiv2022

Integrable Whole-body Orientation Coordinates for Legged Robots

Complex multibody legged robots can have complex rotational control challenges. In this paper, we propose a concise way to understand and formulate a \emph{whole-body orientation} that (i) depends on system configuration only and not a history of motion, (ii) can be representative of the orientation of the entire system while not being attached to any specific link, and (iii) has a rate of change that approximates total system angular momentum. We relate this orientation coordinate to past work, and discuss and demonstrate, including on hardware, several different uses for it.

cs.RO↗

arXiv2022

Core-collapse Supernova Constraint on the Origin of Sterile Neutrino Dark Matter via Neutrino Self-interactions

Novel neutrino self-interaction can open up viable parameter space for the relic abundance of sterile-neutrino dark matter (S$ν$DM). In this work, we constrain the relic target using core-collapse supernova which features the same fundamental process and a similar environment to the early universe era when S$ν$DM is dominantly produced. We present a detailed calculation of the effects of a massive scalar mediated neutrino self-interaction on the supernova cooling rate, including the derivation of the thermal potential in the presence of non-zero chemical potentials from plasma species. Our results demonstrate that the supernova cooling argument can cover the neutrino self-interaction parameter space that complements terrestrial and cosmological probes.

hep-ph↗

arXiv2019

Optimal Reduced-order Modeling of Bipedal Locomotion

State-of-the-art approaches to legged locomotion are widely dependent on the use of models like the linear inverted pendulum (LIP) and the spring-loaded inverted pendulum (SLIP), popular because their simplicity enables a wide array of tools for planning, control, and analysis. However, they inevitably limit the ability to execute complex tasks or agile maneuvers. In this work, we aim to automatically synthesize models that remain low-dimensional but retain the capabilities of the high-dimensional system. For example, if one were to restore a small degree of complexity to LIP, SLIP, or a similar model, our approach discovers the form of that additional complexity which optimizes performance. In this paper, we define a class of reduced-order models and provide an algorithm for optimization within this class. To demonstrate our method, we optimize models for walking at a range of speeds and ground inclines, for both a five-link model and the Cassie bipedal robot.

cs.RO↗

arXiv2017

Learning Stable and Energetically Economical Walking with RAMone

In this paper, we optimize over the control parameter space of our planar-bipedal robot, RAMone, for stable and energetically economical walking at various speeds. We formulate this task as an episodic reinforcement learning problem and use Covariance Matrix Adaptation. The parameters we are interested in modifying include gains from our Hybrid Zero Dynamics style controller and from RAMone's low-level motor controllers.

cs.RO↗