PyTorchKR Papers

최신 논문

총 403편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2308.13491

Towards Optimal Head-to-head Autonomous Racing with Curriculum Reinforcement Learning

Head-to-head autonomous racing is a challenging problem, as the vehicle needs to operate at the friction or handling limits in order to achieve minimum lap times while also actively looking for strategies to overtake/stay ahead of the opponent. In this work we propose a head-to-head racing environment for reinforcement learning which accurately models vehicle dynamics. Some previous works have tried learning a policy directly in the complex vehicle dynamics environment but have failed to learn an optimal policy. In this work, we propose a curriculum learning-based framework by transitioning from a simpler vehicle model to a more complex real environment to teach the reinforcement learning agent a policy closer to the optimal policy. We also propose a control barrier function-based safe reinforcement learning algorithm to enforce the safety of the agent in a more effective way while not compromising on optimality.

arXiv:2308.05514

Advanced-Glycation Endproducts: How cross-linking properties affect the collagen fibril behavior

Advanced-Glycation-Endproducts (AGEs) are known to be a major cause of impaired tissue material properties. In collagen fibrils, the main building component of human tissue, these AGEs appear as fibrillar cross-links. When AGEs accumulate in collagen fibrils, a process often caused by diabetes and aging, the mechanical properties of the collagen fibril are altered. However, current knowledge about the mechanical properties of different types of AGEs, and their quantity in collagen fibrils is limited owing to the scarcity of available experimental data. Consequently, the precise relationship between the nano-scale cross-link properties, their density in collagen fibrils, and the mechanical properties of the collagen fibrils at larger scales remains poorly understood. In our study, we use coarse-grained molecular dynamics simulations and perform destructive tensile tests on collagen fibrils to evaluate the effect of different cross-link densities and their mechanical properties on collagen fibril deformation and fracture behavior. We observe that the collagen fibril stiffens at high strain levels when either the AGEs density or the loading energy capacity of AGEs are increased. We demonstrate that this stiffening is caused by a mechanism that favors energy absorption via stretching rather than inter-molecular sliding. Hence, in cross-linked collagen fibrils, the absorbed energy is stored rather than dissipated through friction, resulting in brittle fracture upon fibrillar failure. Further, by varying multiple AGEs nano-scale parameters, we show that the AGEs loading energy capacity is, aside from their density in the fibril, the unique factor determining the effect of different types of AGEs on the mechanical behavior of collagen fibrils. Our results show that knowing AGEs properties is crucial for understanding of the origin of impaired tissue behavior.

arXiv:2308.01123공식 코드 · Papers with Code

Planar Friction Modelling with LuGre Dynamics and Limit Surfaces

During planar motion, contact surfaces exhibit a coupling between tangential and rotational friction forces. This paper proposes planar friction models grounded in the LuGre model and limit surface theory. First, distributed planar extended state models are proposed and the Elasto-Plastic model is extended for multi-dimensional friction. Subsequently, we derive a reduced planar friction model, coupled with a pre-calculated limit surface, that offers reduced computational cost. The limit surface approximation through an ellipsoid is discussed. The properties of the planar friction models are assessed in various simulations, demonstrating that the reduced planar friction model achieves comparable performance to the distributed model while exhibiting ~80 times lower computational cost.

arXiv:2307.10060

Accurate deep learning sub-grid scale models for large eddy simulations

We present two families of sub-grid scale (SGS) turbulence models developed for large-eddy simulation (LES) purposes. Their development required the formulation of physics-informed robust and efficient Deep Learning (DL) algorithms which, unlike state-of-the-art analytical modeling techniques can produce high-order complex non-linear relations between inputs and outputs. Explicit filtering of data from direct simulations of the canonical channel flow at two friction Reynolds numbers $Re_\tau\approx 395$ and 590 provided accurate data for training and testing. The two sets of models use different network architectures. One of the architectures uses tensor basis neural networks (TBNN) and embeds the simplified analytical model form of the general effective-viscosity hypothesis, thus incorporating the Galilean, rotational and reflectional invariances. The other architecture is that of a relatively simple network, that is able to incorporate the Galilean invariance only. However, this simpler architecture has better feature extraction capacity owing to its ability to establish relations between and extract information from cross-components of the integrity basis tensors and the SGS stresses. Both sets of models are used to predict the SGS stresses for feature datasets generated with different filter widths, and at different Reynolds numbers. It is shown that due to the simpler model's better feature learning capabilities, it outperforms the invariance embedded model in statistical performance metrics. In a priori tests, both sets of models provide similar levels of dissipation and backscatter. Based on the test results, both sets of models should be usable in a posteriori actual LESs.

arXiv:2307.09206

Context-Conditional Navigation with a Learning-Based Terrain- and Robot-Aware Dynamics Model

In autonomous navigation settings, several quantities can be subject to variations. Terrain properties such as friction coefficients may vary over time depending on the location of the robot. Also, the dynamics of the robot may change due to, e.g., different payloads, changing the system's mass, or wear and tear, changing actuator gains or joint friction. An autonomous agent should thus be able to adapt to such variations. In this paper, we develop a novel probabilistic, terrain- and robot-aware forward dynamics model, termed TRADYN, which is able to adapt to the above-mentioned variations. It builds on recent advances in meta-learning forward dynamics models based on Neural Processes. We evaluate our method in a simulated 2D navigation setting with a unicycle-like robot and different terrain layouts with spatially varying friction coefficients. In our experiments, the proposed model exhibits lower prediction error for the task of long-horizon trajectory prediction, compared to non-adaptive ablation models. We also evaluate our model on the downstream task of navigation planning, which demonstrates improved performance in planning control-efficient paths by taking robot and terrain properties into account.

arXiv:2306.15668

Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties

General physical scene understanding requires more than simply localizing and recognizing objects -- it requires knowledge that objects can have different latent properties (e.g., mass or elasticity), and that those properties affect the outcome of physical events. While there has been great progress in physical and video prediction models in recent years, benchmarks to test their performance typically do not require an understanding that objects have individual physical properties, or at best test only those properties that are directly observable (e.g., size or color). This work proposes a novel dataset and benchmark, termed Physion++, that rigorously evaluates visual physical prediction in artificial systems under circumstances where those predictions rely on accurate estimates of the latent physical properties of objects in the scene. Specifically, we test scenarios where accurate prediction relies on estimates of properties such as mass, friction, elasticity, and deformability, and where the values of those properties can only be inferred by observing how objects move and interact with other objects or fluids. We evaluate the performance of a number of state-of-the-art prediction models that span a variety of levels of learning vs. built-in knowledge, and compare that performance to a set of human predictions. We find that models that have been trained using standard regimes and datasets do not spontaneously learn to make inferences about latent properties, but also that models that encode objectness and physical states tend to make better predictions. However, there is still a huge gap between all models and human performance, and all models' predictions correlate poorly with those made by humans, suggesting that no state-of-the-art model is learning to make physical predictions in a human-like way. Project page: https://dingmyu.github.io/physion_v2/

arXiv:2306.14730

An Exploration-Exploitation Approach to Anti-lock Brake Systems

Anti-lock Brake System (ABS) is a mandatory active safety feature on road vehicles with analogous systems for aircraft and locomotives. This feature aims to prevent locking of the wheels when braking and to improve the handling performance, as well as reduce stopping distance of the vehicle. Estimation uncertainties in the vehicle state and environment (road surface) are often neglected or handled separately from the ABS controller, leading to sub-optimal braking. In this paper, a Dual Control for Exploration-Exploitation (DCEE) approach is taken toward the ABS problem which achieves both accurate state (and environment) estimation and superior braking performance. Compared with popular Extremum Seeking methods, improvements of up to $15\%$ and $8.5\%$ are shown in stopping time and stopping distance, respectively. A Regularized Particle Filter with Markov Chain Monte Carlo step is used to estimate vehicle states and parameters of the Magic Formula tyre model that includes the peak friction coefficient for the environment. The effectiveness of the DCEE approach is demonstrated across a range of driving scenarios such as low and high speeds; snow, wet and dry roads and changing road surfaces.

arXiv:2306.06530

Use of Robust DOB/CDOB Compensation to Improve Autonomous Vehicle Path Following Performance in the Presence of Model Uncertainty, CAN Bus Delays and External Disturbances

A path tracking control system is chosen as the proof-of-concept demonstration application in this paper. A disturbance observer (DOB) is embedded within the steering to path error automated driving loop to handle uncertain parameters such as vehicle mass, vehicle velocities and road friction coefficient and to reject yaw moment disturbances. The compensation of vehicle model with the embedded disturbance observer forces it to behave like its nominal model within the bandwidth of the disturbance observer. A parameter space approach based steering controller is then used to optimize performance. The proposed method demonstrates good disturbance rejection and achieves stability robustness. The variable time delay from the steer-by-wire system in an actual vehicle can also lead to stability issues since it adds large negative phase angle to the plant frequency response and tends to destabilize it. A communication disturbance observer (CDOB) based time delay compensation approach that does not require exact knowledge of this time delay is embedded into the steering actuation loop to handle this problem. Stability analysis of both DOB and CDOB compensation system are presented in this paper. Extensive model-in-the-loop simulations were performed to test the designed disturbance observer and CDOB systems and show reduced path following errors in the presence of uncertainty, disturbances and time delay. A validated model of our 2017 Ford Fusion Hybrid research autonomous vehicle is used in the simulation analyses. Simulation results verify the performance enhancement of the vehicle path following control with proposed DOB and CDOB structure. A HiL simulator that uses a validated CarSim model with sensors and traffic will be used later to verify the real time capability of our approach.

arXiv:2306.03887

Fast Context Adaptation in Cost-Aware Continual Learning

In the past few years, DRL has become a valuable solution to automatically learn efficient resource management strategies in complex networks with time-varying statistics. However, the increased complexity of 5G and Beyond networks requires correspondingly more complex learning agents and the learning process itself might end up competing with users for communication and computational resources. This creates friction: on the one hand, the learning process needs resources to quickly convergence to an effective strategy; on the other hand, the learning process needs to be efficient, i.e., take as few resources as possible from the user's data plane, so as not to throttle users' QoS. In this paper, we investigate this trade-off and propose a dynamic strategy to balance the resources assigned to the data plane and those reserved for learning. With the proposed approach, a learning agent can quickly converge to an efficient resource allocation strategy and adapt to changes in the environment as for the CL paradigm, while minimizing the impact on the users' QoS. Simulation results show that the proposed method outperforms static allocation methods with minimal learning overhead, almost reaching the performance of an ideal out-of-band CL solution.

arXiv:2305.15870

Robust asymptotic observer of motion states with nonlinear friction

This paper revisits the previously proposed linear asymptotic observer of the motion state variables with nonlinear friction and provides a robust design suitable for both, transient presliding and steady-state sliding phases of the relative motion. The class of motion systems with the only measurable output displacement is considered. The reduced-order Luenberger type observer is designed based on the obtained simplified state-space representation with a time-varying system matrix. The resulted observation error dynamics proves to be robust and appropriate for all variations of the system matrix, which are due to the nonlinear spatially varying friction. A specially designed tribological setup to accurately monitor the relative motion between two contacting friction surfaces is used to collect the experimental data of the deceleration trajectories when excited by a series of impulses. The performance of the state estimation using the proposed observer is shown based on the collected experimental data.

arXiv:2305.14449

Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding

Conversational AI systems such as Alexa need to understand defective queries to ensure robust conversational understanding and reduce user friction. These defective queries often arise from user ambiguities, mistakes, or errors in automatic speech recognition (ASR) and natural language understanding (NLU). Personalized query rewriting is an approach that focuses on reducing defects in queries by taking into account the user's individual behavior and preferences. It typically relies on an index of past successful user interactions with the conversational AI. However, unseen interactions within the user's history present additional challenges for personalized query rewriting. This paper presents our "Collaborative Query Rewriting" approach, which specifically addresses the task of rewriting new user interactions that have not been previously observed in the user's history. This approach builds a "User Feedback Interaction Graph" (FIG) of historical user-entity interactions and leverages multi-hop graph traversal to enrich each user's index to cover future unseen defective queries. The enriched user index is called a Collaborative User Index and contains hundreds of additional entries. To counteract precision degradation from the enlarged index, we add additional transformer layers to the L1 retrieval model and incorporate graph-based and guardrail features into the L2 ranking model. Since the user index can be pre-computed, we further investigate the utilization of a Large Language Model (LLM) to enhance the FIG for user-entity link prediction in the Video/Music domains. Specifically, this paper investigates the Dolly-V2 7B model. We found that the user index augmented by the fine-tuned Dolly-V2 generation significantly enhanced the coverage of future unseen user interactions, thereby boosting QR performance on unseen queries compared with the graph traversal only approach.

arXiv:2305.03798

Friction-Adaptive Stochastic Nonlinear Model Predictive Control for Autonomous Vehicles

This paper addresses the trajectory-tracking problem under uncertain road-surface conditions for autonomous vehicles. We propose a stochastic nonlinear model predictive controller (SNMPC) that learns a tire--road friction model online using standard automotive-grade sensors. Learning the entire tire--road friction model in real time requires driving in the nonlinear, potentially unstable regime of the vehicle dynamics, using a prediction model that may not have fully converged. To handle this, we formulate the tire-friction model learning in a Bayesian framework, and propose two estimators that learn different aspects of the tire--road friction. The estimators output the estimate of the tire-friction model as well as the uncertainty of the estimate, which expresses the confidence in the model for different driving regimes. The SNMPC exploits the uncertainty estimate in its prediction model to take proper action when the uncertainty is large. We validate the approach in an extensive Monte-Carlo study using real vehicle parameters and in CarSim. The results when comparing to various MPC approaches indicate a substantial reduction in constraint violations, as well as a reduction in closed-loop cost. We also demonstrate the real-time feasibility in automotive-grade processors using a dSPACE MicroAutoBox-II rapid prototyping unit, showing a worst-case computation time of roughly 40ms.

arXiv:2304.11504

Preference Evolution under Partner Choice

We present a model that investigates preference evolution with endogenous matching. In the short run, individuals' subjective preferences influence partner selection and behavior in strategic interactions, which affect their material payoffs. These payoffs, in turn, determine how preferences evolve in the long run. To properly model the "match-to-interact" process, we combine stable matching and equilibrium concepts. Our analysis shows that endogenous matching gives rise to the evolutionary stability of a class of preferences that exhibit both affinity bias and efficient play. Such preferences stand out in the evolutionary process because they are able to force positive assortative matching and joint payoff maximization. Under incomplete information, a strong form of affinity bias, parochialism, is necessary for a preference to prevail in evolution, because stronger incentives are required to engage in self-sorting with information friction.

arXiv:2304.12263

A hierarchical adaptive nonlinear model predictive control approach for maximizing tire force usage in autonomous vehicles

The ability to reliably maximize tire force usage would improve the safety of autonomous vehicles, especially in challenging edge cases. However, vehicle control near the limits of handling has many challenges, including robustly contending with tire force saturation, balancing model fidelity and computational efficiency, and coordinating inputs with the lower level chassis control system. This work studies Nonlinear Model Predictive Control for limit handling, specifically adapting to changing tire-road conditions and maximally allocating tire force utilization. We present a novel hierarchical framework that combines a single-track model with longitudinal weight transfer dynamics in the predictive control layer, with lateral brake distribution occurring at the chassis control layer. This vehicle model is simultaneously used in an Unscented Kalman Filter for online friction estimation. Comparative experiments on a full-scale vehicle operating on a race track at up to 95% of maximum tire force usage demonstrate the overall practical effectiveness of this approach.

arXiv:2304.09047

Neural Lumped Parameter Differential Equations with Application in Friction-Stir Processing

Lumped parameter methods aim to simplify the evolution of spatially-extended or continuous physical systems to that of a "lumped" element representative of the physical scales of the modeled system. For systems where the definition of a lumped element or its associated physics may be unknown, modeling tasks may be restricted to full-fidelity simulations of the physics of a system. In this work, we consider data-driven modeling tasks with limited point-wise measurements of otherwise continuous systems. We build upon the notion of the Universal Differential Equation (UDE) to construct data-driven models for reducing dynamics to that of a lumped parameter and inferring its properties. The flexibility of UDEs allow for composing various known physical priors suitable for application-specific modeling tasks, including lumped parameter methods. The motivating example for this work is the plunge and dwell stages for friction-stir welding; specifically, (i) mapping power input into the tool to a point-measurement of temperature and (ii) using this learned mapping for process control.

arXiv:2304.07070

Who breaks early, looses: goal oriented training of deep neural networks based on port Hamiltonian dynamics

The highly structured energy landscape of the loss as a function of parameters for deep neural networks makes it necessary to use sophisticated optimization strategies in order to discover (local) minima that guarantee reasonable performance. Overcoming less suitable local minima is an important prerequisite and often momentum methods are employed to achieve this. As in other non local optimization procedures, this however creates the necessity to balance between exploration and exploitation. In this work, we suggest an event based control mechanism for switching from exploration to exploitation based on reaching a predefined reduction of the loss function. As we give the momentum method a port Hamiltonian interpretation, we apply the 'heavy ball with friction' interpretation and trigger breaking (or friction) when achieving certain goals. We benchmark our method against standard stochastic gradient descent and provide experimental evidence for improved performance of deep neural networks when our strategy is applied.

arXiv:2303.08965

Robust Pivoting Manipulation using Contact Implicit Bilevel Optimization

Generalizable manipulation requires that robots be able to interact with novel objects and environment. This requirement makes manipulation extremely challenging as a robot has to reason about complex frictional interactions with uncertainty in physical properties of the object and the environment. In this paper, we study robust optimization for planning of pivoting manipulation in the presence of uncertainties. We present insights about how friction can be exploited to compensate for inaccuracies in the estimates of the physical properties during manipulation. Under certain assumptions, we derive analytical expressions for stability margin provided by friction during pivoting manipulation. This margin is then used in a Contact Implicit Bilevel Optimization (CIBO) framework to optimize a trajectory that maximizes this stability margin to provide robustness against uncertainty in several physical parameters of the object. We present analysis of the stability margin with respect to several parameters involved in the underlying bilevel optimization problem. We demonstrate our proposed method using a 6 DoF manipulator for manipulating several different objects. We also design and validate an MPC controller using the proposed algorithm which can track and regulate the position of the object during manipulation.

arXiv:2303.07994

Learning for Precision Motion of an Interventional X-ray System: Add-on Physics-Guided Neural Network Feedforward Control

Tracking performance of physical-model-based feedforward control for interventional X-ray systems is limited by hard-to-model parasitic nonlinear dynamics, such as cable forces and nonlinear friction. In this paper, these nonlinear dynamics are compensated using a physics-guided neural network (PGNN), consisting of a physical model, embedding prior knowledge of the dynamics, in parallel with a neural network to learn hard-to-model dynamics. To ensure that the neural network learns only unmodelled effects, the neural network output in the subspace spanned by the physical model is regularized via an orthogonal projection-based approach, resulting in complementary physical model and neural network contributions. The PGNN feedforward controller reduces the tracking error of an interventional X-ray system by a factor of 5 compared to an optimally tuned physical model, successfully compensating the unmodeled parasitic dynamics.

arXiv:2303.05927

Estimating friction coefficient using generative modelling

It is common to utilise dynamic models to measure the tyre-road friction in real-time. Alternatively, predictive approaches estimate the tyre-road friction by identifying the environmental factors affecting it. This work aims to formulate the problem of friction estimation as a visual perceptual learning task. The problem is broken down into detecting surface characteristics by applying semantic segmentation and using the extracted features to predict the frictional force. This work for the first time formulates the friction estimation problem as a regression from the latent space of a semantic segmentation model. The preliminary results indicate that this approach can estimate frictional force.

arXiv:2303.04236

Optimal investment with insurable background risk and nonlinear portfolio allocation frictions

We study investment and insurance demand decisions for an agent in a theoretical continuous-time expected utility maximization model that combines risky assets with an (exogenous) insurable background risk. This risk takes the form of a jump-diffusion process with negative jumps in the return rate of the (self-financed) wealth. The main distinctive feature of our model is that the agent's decision on portfolio choice and insurance demand causes nonlinear friction in the dynamics of the wealth process. We use the dynamic programming approach to find optimality conditions under which the agent assumes the insurable risk entirely, or partially, or purchases total insurance against it. In particular, we consider differential and piece-wise linear portfolio allocation frictions, with differential borrowing and lending rates as our most emblematic example. Finally, we present a mutual-fund separation result and illustrate our results with several numerical examples when the adverse jump risk has Beta distribution.