arXiv subjects

Suyi Li

Publications and source records attributed to Suyi Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Embodied multi-modal sensing with a soft modular arm powered by physical reservoir computing

Soft robots have become increasingly popular for complex manipulation tasks requiring gentle and safe contact. However, their softness makes accurate control challenging, and high-fidelity sensing is a prerequisite to adequate control performance. To this end, many flexible and embedded sensors have been created over the past decade, but they inevitably increase the robot's complexity and stiffness. This study demonstrates a novel approach that uses simple bending strain gauges embedded inside a modular arm to extract complex information regarding its deformation and working conditions. The core idea is based on physical reservoir computing (PRC): A soft body's rich nonlinear dynamic responses, captured by the inter-connected bending sensor network, could be utilized for complex multi-modal sensing with a simple linear regression algorithm. Our results show that the soft modular arm reservoir can accurately predict body posture (bending angle), estimate payload weight, determine payload orientation, and even differentiate two payloads with only minimal difference in weight -- all using minimal digital computing power.

cs.RO↗

arXiv2024

SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules

Text-to-image (T2I) generation using diffusion models has become a blockbuster service in today's AI cloud. A production T2I service typically involves a serving workflow where a base diffusion model is augmented with various "add-on" modules, notably ControlNet and LoRA, to enhance image generation control. Compared to serving the base model alone, these add-on modules introduce significant loading and computational overhead, resulting in increased latency. In this paper, we present SwiftDiffusion, a system that efficiently serves a T2I workflow through a holistic approach. SwiftDiffusion decouples ControNet from the base model and deploys it as a separate, independently scaled service on dedicated GPUs, enabling ControlNet caching, parallelization, and sharing. To mitigate the high loading overhead of LoRA serving, SwiftDiffusion employs a bounded asynchronous LoRA loading (BAL) technique, allowing LoRA loading to overlap with the initial base model execution by up to k steps without compromising image quality. Furthermore, SwiftDiffusion optimizes base model execution with a novel latent parallelism technique. Collectively, these designs enable SwiftDiffusion to outperform the state-of-the-art T2I serving systems, achieving up to 7.8x latency reduction and 1.6x throughput improvement in serving SDXL models on H800 GPUs, without sacrificing image quality.

cs.DC↗

arXiv2024

Proprioceptive and Exteroceptive Information Perception in a Fabric Soft Robotic Arm via Physical Reservoir Computing with minimal training data

Over the past decades, we have witnessed a rapid emergence of soft and reconfigurable robots thanks to their capability to interact safely with humans and adapt to complex environments. However, their softness makes accurate control very challenging. High-fidelity sensing is critical in improving control performance, especially posture and contact estimation. To this end, traditional camera-based sensors and load cells have limited portability and accuracy, and they will inevitably increase the robot's cost and weight. In this study, instead of using specialized sensors, we only collect distributed pressure data inside a pneumatics-driven soft arm and apply the physical reservoir computing principle to simultaneously predict its kinematic posture (i.e., bending angle) and payload status (i.e., payload mass). Our results show that, with careful readout training, one can obtain accurate bending angle and payload mass predictions via simple, weighted linear summations of pressure readings. In addition, our comparative analysis shows that, to guarantee low prediction errors within 10\%, bending angle prediction requires less training data than payload prediction. This result reveals that balanced linear and nonlinear body dynamics are critical for the physical reservoir to accomplish complex proprioceptive and exteroceptive information perception tasks. Finally, the method of exploring the most efficient readout training methods presented in this paper could be extended to other soft robotic systems to maximize their perception capabilities.

cs.RO↗

arXiv2024

"Golden Ratio Yoshimura" for Meta-Stable and Massively Reconfigurable Deployment

Yoshimura origami is a classical folding pattern that has inspired many deployable structure designs. Its applications span from space exploration, kinetic architectures, and soft robots to even everyday household items. However, despite its wide usage, Yoshimura has been fixated on a set of design constraints to ensure its flat-foldability. Through extensive kinematic analysis and prototype tests, this study presents a new Yoshimura that intentionally defies these constraints. Remarkably, one can impart a unique meta-stability by using the Golden Ratio angle to define the triangular facets of a generalized Yoshimura. As a result, when its facets are strategically popped out, a ``Golden Ratio Yoshimura'' boom with $m$ modules can be theoretically reconfigured into $8^m$ geometrically unique and load-bearing shapes. This result not only challenges the existing design norms but also opens up a new avenue to create deployable and versatile structural systems.

cs.RO↗

arXiv2024

Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning

Compositional Zero-shot Learning (CZSL) aims to identify novel compositions via known attribute-object pairs. The primary challenge in CZSL tasks lies in the significant discrepancies introduced by the complex interaction between the visual primitives of attribute and object, consequently decreasing the classification performance towards novel compositions. Previous remarkable works primarily addressed this issue by focusing on disentangling strategy or utilizing object-based conditional probabilities to constrain the selection space of attributes. Unfortunately, few studies have explored the problem from the perspective of modeling the mechanism of visual primitive interactions. Inspired by the success of vanilla adversarial learning in Cross-Domain Few-Shot Learning, we take a step further and devise a model-agnostic and Primitive-Based Adversarial training (PBadv) method to deal with this problem. Besides, the latest studies highlight the weakness of the perception of hard compositions even under data-balanced conditions. To this end, we propose a novel over-sampling strategy with object-similarity guidance to augment target compositional training data. We performed detailed quantitative analysis and retrieval experiments on well-established datasets, such as UT-Zappos50K, MIT-States, and C-GQA, to validate the effectiveness of our proposed method, and the state-of-the-art (SOTA) performance demonstrates the superiority of our approach. The code is available at https://github.com/lisuyi/PBadv_czsl.

cs.CV↗

arXiv2024

CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference

Pre-trained large language models (LLMs) often need specialization for domain-specific tasks. Low-Rank Adaptation (LoRA) is a popular approach that adapts a base model to multiple tasks by adding lightweight trainable adapters. In this paper, we present CaraServe, a system that efficiently serves many LoRA adapters derived from a common base model. CaraServe maintains the base model on GPUs and dynamically loads activated LoRA adapters from main memory. As GPU loading results in a cold-start that substantially delays token generation, CaraServe employs a CPU-assisted approach. It early starts the activated adapters on CPUs for prefilling as they are being loaded onto GPUs; after loading completes, it then switches to the GPUs for generative LoRA inference. CaraServe develops a highly optimized synchronization mechanism to efficiently coordinate LoRA computation on the CPU and GPU. Moreover, CaraServe employs a rank-aware scheduling algorithm to optimally schedule heterogeneous LoRA requests for maximum service-level objective (SLO) attainment. We have implemented CaraServe and evaluated it against state-of-the-art LoRA serving systems. Our results demonstrate that CaraServe can speed up the average request serving latency by up to 1.4$\times$ and achieve an SLO attainment of up to 99%.

cs.DC↗

arXiv2023

Self-Sustained And Coordinated Rhythmic Deformations With SMA For Controller-Free Locomotion

This study presents a modular, electronics-free, and fully onboard control and actuation approach for SMA-based soft robots to achieve locomotion tasks. This approach exploits the nonlinear mechanics of compliant curved beams and carefully designed mechanical control circuits to create and synchronize rhythmic deformation cycles, mimicking the central pattern generators (CPG) prevalent in animal locomotions. More specifically, the study elucidates a new strategy to amplify the actuation performance of the shape memory coil actuator by coupling it to a carefully designed, mono-stable curve beam with a snap-through buckling behavior. Such SMA-curved beam assembly is integrated with an entirely mechanical circuit featuring a slider mechanism. This circuit can automatically cut off and supply current to the SMA according to its deformation status, generating a self-sustained rhythmic deformation cycle using a simple DC power supply. Finally, this study presents a new strategy to coordinate (synchronize) two rhythmic deformation cycles from two robotic modules to achieve efficient crawling locomotion but still use a single DC power. This work represents a significant step towards fully autonomous, electronics-free SMA-based locomotion robots with fully onboard actuation and control.

cs.RO↗

arXiv2023

Building Intelligence in the Mechanical Domain -- Harvesting the Reservoir Computing Power in Origami to Achieve Information Perception Tasks

In this paper, we experimentally examine the cognitive capability of a simple, paper-based Miura-ori -- using the physical reservoir computing framework -- to achieve different information perception tasks. The body dynamics of Miura-ori (aka. its vertices displacements), which is excited by a simple harmonic base excitation, can be exploited as the reservoir computing resource. By recording these dynamics with a high-resolution camera and image processing program and then using linear regression for training, we show that the origami reservoir has sufficient computing capacity to estimate the weight and position of a payload. It can also recognize the input frequency and magnitude patterns. Furthermore, multitasking is achievable by simultaneously applying two targeted functions to the same reservoir state matrix. Therefore, we demonstrate that Miura-ori can assess the dynamic interactions between its body and ambient environment to extract meaningful information -- an intelligent behavior in the mechanical domain. Given that Miura-ori has been widely used to construct deployable structures, lightweight materials, and compliant robots, enabling such information perception tasks can add a new dimension to the functionality of such a versatile structure.

cs.ET↗

arXiv2022

Phononic Bandgap Programming in Kirigami

This study investigates the programming of elastic wave propagation bandgaps in a kirigami material by intentionally sequencing its constitutive mechanical bits. Such sequencing exploits the multi-stable nature of the stretched kirigami, allowing each mechanical bit to switch between two stable equilibria with different external shapes (aka. "(0)" and "(1)" states). Therefore, by designing the sequence of (0) and (1) bits, one can fundamentally change the underlying periodicity and thus program the phononic bandgap frequencies. To this end, this study develops an algorithm to identify the unique periodicities generated by assembling "$n$-bit strings" consisting of $n$ mechanical bits. Based on a simplified geometry of these $n$-bit strings, this study also formulates a theory to uncover the rich mapping between input sequencing and output bandgaps. The theoretical prediction and experiment results confirm that the (0) and (1) bit sequencing is a versatile approach to programming the phonic bandgap frequencies. Moreover, one can additionally fine-tune the bandgaps by adjusting the global stretch. Overall, the results of this study elucidate new strategies for programming the dynamic responses of architected material systems.

cond-mat.mtrl-sci↗

arXiv2021

Tunable Wave Propagation Bandgap Via Stretching kirigami Sheets

This study examines the Braggs bandgap and its mechanical tuning in a stretch-buckled kirigami sheet with "zig-zag" distributed parallel cuts. When stretched beyond a critical threshold, the kirigami buckles out-of-plane and generates a 3D periodic architecture. Our theoretical calculation, numerical simulation, and experiments confirm the transverse elastic wave propagation bandgaps and their correlation to stretching. This result opens an avenue of using kirigami as a simple and effective approach for creating and adapting periodicity for wave propagation control.

cond-mat.mtrl-sci↗

arXiv2021

Asymmetric Multi-Stability from Relaxing the Rigid-Folding Conditions in a Stacked Miura-ori Cellular Solid

Traditionally, origami has been categorized into two groups according to their kinematics design: rigid and non-rigid origami. However, such categorization can be superficial, and rigid origami can obtain new mechanical properties by intentionally relaxing the rigid-folding kinematics. Based on numerical simulations using the bar-hinge approach and experiments, this study examines the multi-stability of a stacked Miura-origami cellular structure with different levels of facet compliance. The simulation and experiment results show that a unit cell in such cellular solid exhibits only two stable states if it follows the rigid origami kinematics; however, two more stable states are reachable if the origami facets become sufficiently compliant. Moreover, the switch between two certain stable states shows an asymmetric energy barrier, meaning that the unit cell follows fundamentally different deformation paths when it extends from one state to another compared to the opposite compression switch. As a result, the reaction force required for extending this unit cell between these two states can be higher than the compression switch. Such asymmetric multi-stability can be fine-tuned by tailoring the underlying origami design, and it can be extended into cellular solids with carefully placed voids. By showing the benefits of exploiting facet compliance, this study could foster multi-functional structures and material systems that traditional rigid origami cannot create.

physics.app-ph↗

arXiv2021

Physical Reservoir Computing with Origami and its Application to Robotic Crawling

A new paradigm called physical reservoir computing has recently emerged, where the nonlinear dynamics of high-dimensional and fixed physical systems are harnessed as a computational resource to achieve complex tasks. Via extensive simulations based on a dynamic truss-frame model, this study shows that an origami structure can perform as a dynamic reservoir with sufficient computing power to emulate high-order nonlinear systems, generate stable limit cycles, and modulate outputs according to dynamic inputs. This study also uncovers the linkages between the origami reservoir's physical designs and its computing power, offering a guideline to optimize the computing performance. Comprehensive parametric studies show that selecting optimal feedback crease distribution and fine-tuning the underlying origami folding designs are the most effective approach to improve computing performance. Furthermore, this study shows how origami's physical reservoir computing power can apply to soft robotic control problems by a case study of earthworm-like peristaltic crawling without traditional controllers. These results can pave the way for origami-based robots with embodied mechanical intelligence.

cs.RO↗

arXiv2020

Exploiting the Nonlinear Stiffness of TMP Origami Folding to Enhance Robotic Jumping Performance

Via numerical simulation and experimental assessment, this study examines the use of origami folding to develop robotic jumping mechanisms with tailored nonlinear stiffness to improve dynamic performance. Specifically, we use Tachi-Miura Polyhedron (TMP) bellow origami -- which exhibits a nonlinear "strain-softening" force-displacement curve -- as a jumping robotic skeleton with embedded energy storage. TMP's nonlinear stiffness allows it to store more energy than a linear spring and offers improved jumping height and airtime. Moreover, the nonlinearity can be tailored by directly changing the underlying TMP crease geometry. A critical challenge is to minimize the TMP's hysteresis and energy loss during its compression stage right before jumping. So we used the plastically annealed lamina emergent origami (PALEO) concept to modify the TMP creases. PALEO increases the folding limit before plastic deformation occurs, thus improving the overall strain energy retention. Jumping experiments confirmed that a nonlinear TMP mechanism achieved roughly 9% improvement in air time and a 13% improvement in jumping height compared to a "control" TMP sample with a relatively linear stiffness. This study's results validate the advantages of using origami in robotic jumping mechanisms and demonstrate the benefits of utilizing nonlinear spring elements for improving jumping performance. Therefore, they could foster a new family of energetically efficient jumping mechanisms with optimized performance in the future.

cs.RO↗

arXiv2020

Harnessing The Multi-Stability Of Kresling Origami For Reconfigurable Articulation In Soft Robotic Arms

This study examines a biology-inspired approach of using reconfigurable articulation to reduce the control requirement for soft robotic arms. We construct a robotic arm by assembling Kresling origami modules that exhibit predictable bistability. Via switching between their two stable states, these origami modules can behave either like a flexible joint with low bending stiffness or like a stiff link with high stiffness, without requiring any continuous power supply. In this way, the robotic arm can exhibit pseudo-linkage kinematics with lower control requirements and improved motion accuracy. A unique advantage of using origami as the robotic arm skeleton is that its bending stiffness ratio between stable states is directly related to the underlying Kresling design. Therefore, we conduct extensive parametric analyses and experimental validations to identify the optimized Kresling pattern for articulation. The results indicate that a higher angle ratio, a smaller resting length at contracted stable state, and a large number of polygon sides can offer more significant and robust bending stiffness tuning. Based on this insight, we construct a proof-of-concept, tendon-driven robotic arm consisting of three modules, and show that it can exhibit the desired reconfigurable articulation behavior. Moreover, the deformations of this manipulator are consistent with kinematic model predictions, which validate the possibility of using simple controllers for such compliant robotic systems.

physics.app-ph↗

arXiv2020

Dynamic Folding of Origami By Exploiting Asymmetric Multi-Stability

In this study, we examine a rapid and reversible origami folding method by exploiting a combination of resonance excitation, asymmetric multi-stability, and active control. The underlying idea is that, by harmonically exciting a multi-stable origami at its resonance frequencies, one can induce rapid folding between its different stable equilibria without the need for using responsive materials. To this end, we use a bi-stable water-bomb base as an archetypal example. Via numerical simulation based on a new dynamic model and experimental testing, we show that the inherent asymmetry of waterbomb bi-stability can enable dynamic folding with relatively low actuation requirements. For example, if the water-bomb initially settles at its "weak" stable state, one can use a base excitation to induce the intra-well resonance. As a result, the origami would fold and remain at the other "strong" stable state even if the excitation does not stop. The origami dynamics starting from the strong state, on the other hand, is more complicated. The water-bomb origami is prone to show inter-well oscillation rather than a uni-directional switch due to a nonlinear relationship between the dynamic folding behavior, asymmetric potential energy barrier, the difference in resonance frequencies, and excitation amplitude. Therefore, we develop an active feedback control strategy, which cuts off the base excitation input at the critical moment to achieve robust and uni-directional folding from the strong stable state to the weak one. The results of this study can apply to many different kinds of origami and create a new approach for rapid and reversible (self-)folding, thus advancing the application of origami in shape morphing systems, adaptive structures, and reconfigurable robotics.

physics.app-ph↗

arXiv2020

Learning to Detect Malicious Clients for Robust Federated Learning

Federated learning systems are vulnerable to attacks from malicious clients. As the central server in the system cannot govern the behaviors of the clients, a rogue client may initiate an attack by sending malicious model updates to the server, so as to degrade the learning performance or enforce targeted model poisoning attacks (a.k.a. backdoor attacks). Therefore, timely detecting these malicious model updates and the underlying attackers becomes critically important. In this work, we propose a new framework for robust federated learning where the central server learns to detect and remove the malicious model updates using a powerful detection model, leading to targeted defense. We evaluate our solution in both image classification and sentiment analysis tasks with a variety of machine learning models. Experimental results show that our solution ensures robust federated learning that is resilient to both the Byzantine attacks and the targeted model poisoning attacks.

cs.LG↗

arXiv2019

Abnormal Client Behavior Detection in Federated Learning

In federated learning systems, clients are autonomous in that their behaviors are not fully governed by the server. Consequently, a client may intentionally or unintentionally deviate from the prescribed course of federated model training, resulting in abnormal behaviors, such as turning into a malicious attacker or a malfunctioning client. Timely detecting those anomalous clients is therefore critical to minimize their adverse impacts. In this work, we propose to detect anomalous clients at the server side. In particular, we generate low-dimensional surrogates of model weight vectors and use them to perform anomaly detection. We evaluate our solution through experiments on image classification model training over the FEMNIST dataset. Experimental results show that the proposed detection-based approach significantly outperforms the conventional defense-based methods.

cs.LG↗

arXiv2019

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases

We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems. It consists of 30k+ turns plus 10k+ annotated SQL queries, obtained from a Wizard-of-Oz (WOZ) collection of 3k dialogues querying 200 complex DBs spanning 138 domains. Each dialogue simulates a real-world DB query scenario with a crowd worker as a user exploring the DB and a SQL expert retrieving answers with SQL, clarifying ambiguous questions, or otherwise informing of unanswerable questions. When user questions are answerable by SQL, the expert describes the SQL and execution results to the user, hence maintaining a natural interaction flow. CoSQL introduces new challenges compared to existing task-oriented dialogue datasets:(1) the dialogue states are grounded in SQL, a domain-independent executable representation, instead of domain-specific slot-value pairs, and (2) because testing is done on unseen databases, success requires generalizing to new domains. CoSQL includes three tasks: SQL-grounded dialogue state tracking, response generation from query results, and user dialogue act prediction. We evaluate a set of strong baselines for each task and show that CoSQL presents significant challenges for future research. The dataset, baselines, and leaderboard will be released at https://yale-lily.github.io/cosql.

cs.CL↗