arXiv subjects

Hanbit Oh

Publications and source records attributed to Hanbit Oh.

27 records · Page 2Linked to original sources

arXiv2023

Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks

Partial Automation (PA) with intelligent support systems has been introduced in industrial machinery and advanced automobiles to reduce the burden of long hours of human operation. Under PA, operators perform manual operations (providing actions) and operations that switch to automatic/manual mode (mode-switching). Since PA reduces the total duration of manual operation, these two action and mode-switching operations can be replicated by imitation learning with high sample efficiency. To this end, this paper proposes Disturbance Injection under Partial Automation (DIPA) as a novel imitation learning framework. In DIPA, mode and actions (in the manual mode) are assumed to be observables in each state and are used to learn both action and mode-switching policies. The above learning is robustified by injecting disturbances into the operator's actions to optimize the disturbance's level for minimizing the covariate shift under PA. We experimentally validated the effectiveness of our method for long-horizon tasks in two simulations and a real robot environment and confirmed that our method outperformed the previous methods and reduced the demonstration burden.

cs.RO↗

arXiv2022

Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation

Humans demonstrate a variety of interesting behavioral characteristics when performing tasks, such as selecting between seemingly equivalent optimal actions, performing recovery actions when deviating from the optimal trajectory, or moderating actions in response to sensed risks. However, imitation learning, which attempts to teach robots to perform these same tasks from observations of human demonstrations, often fails to capture such behavior. Specifically, commonly used learning algorithms embody inherent contradictions between the learning assumptions (e.g., single optimal action) and actual human behavior (e.g., multiple optimal actions), thereby limiting robot generalizability, applicability, and demonstration feasibility. To address this, this paper proposes designing imitation learning algorithms with a focus on utilizing human behavioral characteristics, thereby embodying principles for capturing and exploiting actual demonstrator behavioral characteristics. This paper presents the first imitation learning framework, Bayesian Disturbance Injection (BDI), that typifies human behavioral characteristics by incorporating model flexibility, robustification, and risk sensitivity. Bayesian inference is used to learn flexible non-parametric multi-action policies, while simultaneously robustifying policies by injecting risk-sensitive disturbances to induce human recovery action and ensuring demonstration feasibility. Our method is evaluated through risk-sensitive simulations and real-robot experiments (e.g., table-sweep task, shaft-reach task and shaft-insertion task) using the UR5e 6-DOF robotic arm, to demonstrate the improved characterisation of behavior. Results show significant improvement in task performance, through improved flexibility, robustness as well as demonstration feasibility.

cs.RO↗

arXiv2022

Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies

Scenarios requiring humans to choose from multiple seemingly optimal actions are commonplace, however standard imitation learning often fails to capture this behavior. Instead, an over-reliance on replicating expert actions induces inflexible and unstable policies, leading to poor generalizability in an application. To address the problem, this paper presents the first imitation learning framework that incorporates Bayesian variational inference for learning flexible non-parametric multi-action policies, while simultaneously robustifying the policies against sources of error, by introducing and optimizing disturbances to create a richer demonstration dataset. This combinatorial approach forces the policy to adapt to challenging situations, enabling stable multi-action policies to be learned efficiently. The effectiveness of our proposed method is evaluated through simulations and real-robot experiments for a table-sweep task using the UR3 6-DOF robotic arm. Results show that, through improved flexibility and robustness, the learning performance and control safety are better than comparison methods.

cs.RO↗

arXiv2022

Disturbance-Injected Robust Imitation Learning with Task Achievement

Robust imitation learning using disturbance injections overcomes issues of limited variation in demonstrations. However, these methods assume demonstrations are optimal, and that policy stabilization can be learned via simple augmentations. In real-world scenarios, demonstrations are often of diverse-quality, and disturbance injection instead learns sub-optimal policies that fail to replicate desired behavior. To address this issue, this paper proposes a novel imitation learning framework that combines both policy robustification and optimal demonstration learning. Specifically, this combinatorial approach forces policy learning and disturbance injection optimization to focus on mainly learning from high task achievement demonstrations, while utilizing low achievement ones to decrease the number of samples needed. The effectiveness of the proposed method is verified through experiments using an excavation task in both simulations and a real robot, resulting in high-achieving policies that are more stable and robust to diverse-quality demonstrations. In addition, this method utilizes all of the weighted sub-optimal demonstrations without eliminating them, resulting in practical data efficiency benefits.

cs.RO↗

arXiv2021

Using Disorder to Identify Bogoliubov Fermi-Surface States

We argue that a superconducting state with a Fermi-surface of Bogoliubov quasiparticles, a Bogoliubov Fermi-surface (BG-FS), can be identified by the dependence of physical quantities on disorder. In particular, we show that a linear dependence of the residual density of states at weak disorder distinguishes a BG-FS state from other nodal superconducting states. We further demonstrate the stability of supercurrent against impurities and a characteristic Drude-like behavior of the optical conductivity. Our results can be directly applied to electron irradiation experiments on candidate materials of BG-FSs, including Sr$_2$RuO$_4$, FeSe$_{1-x}$S$_x$, and UBe$_{13}$.

cond-mat.str-el↗

arXiv2021

Exotic Thermal Transitions with Spontaneous Symmetry Breaking

We show that exotic spontaneous symmetry breaking appears in thermal topological phases by perturbing the exact solutions of quantum rotor models coupled to the three-dimensional toric code. The exotic Ising and XY transitions are shown to be in the same universality class in drastic contrast to the conventional Wilson-Fisher classes without topological orders. Our results indicate that topological orders must be included to pin down universality classes of thermal transitions in addition to order parameter symmetry and spatial dimension. We evaluate all the critical exponents and find that the exotic universality class is more stable under the couplings to acoustic phonons and disorder. Applying our results to experiments, we provide a plausible scenario in puzzlings of strongly correlated systems, including the absence of specific heat anomaly in doped RbFe$_2$As$_2$.

cond-mat.str-el↗

arXiv2020

Proximity-induced hidden order transition in a correlated heterostructure Sr$_2$VO$_3$FeAs

Symmetry is one of the most significant concepts in physics, and its importance has been largely manifested in phase transitions by its spontaneous breaking. In strongly correlated systems, however, mysterious and enigmatic phase transitions, inapplicable of the symmetry description, have been discovered and often dubbed hidden order transitions, as found in, $\it{e.g.}$, high-$T_C$ cuprates, heavy fermion superconductors, and quantum spin liquid candidates. Here, we report a new type of hidden order transition in a correlated heterostructure Sr$_2$VO$_3$FeAs, whose origin is attributed to an unusually enhanced Kondo-type proximity coupling between localized spins of V and itinerant electrons of FeAs. Most notably, a fully isotropic gap opening, identified by angle-resolved photoemission spectroscopy, occurs selectively in one of the Fermi surfaces below $T_{\rm HO}$ $\sim$ 150 K, associated with a singular behavior of the specific heat and a strong enhancement on the anisotropic magnetoresistance. These observations are incompatible with the prevalent broken-symmetry-driven scenarios of electronic gap opening and highlight a critical role of proximity coupling. Our findings demonstrate that correlated heterostructures offer a novel platform for design and engineering of exotic hidden order phases.

cond-mat.str-el↗

arXiv2020

Instability of $j= 3/2$ Bogoliubov Fermi-surfaces

Exotic quantum phases including topological states and non-Fermi liquids may be realized by quantum states with total angular momentum $j=3/2$, as manifested in HgTe and pyrochlore iridates. Recently, an exotic superconducting state with non-zero density of states of zero energy Bogoliubov (BG) quasiparticles, Bogoliubov Fermi-surface (BG-FS), was also proposed in a centrosymmetric $j=3/2$ system, protected by a Z$_2$ topological invariant. Here, we consider interaction effects of a centrosymmetric BG-FS and demonstrate its instability by using mean-field and renormalization group analysis. The Bardeen-Cooper-Schrieffer (BCS) type logarithmical enhancement is shown in fluctuation channels associated with inversion symmetry. Thus, we claim that the inversion symmetry instability is an intrinsic characteristic of a BG-FS under generic attractive interactions between BG quasiparticles. In drastic contrast to the standard BCS superconductivity, a Fermi-surface may generically survive even with the instability. We propose the experimental setup, a second harmonic generation experiment with a strain gradient, to detect the instability. Possible applications to iron based superconductors and heavy fermion systems including FeSe are also discussed.

cond-mat.str-el↗

arXiv2019

Multi-scale Quantum Criticality driven by Kondo-lattice Coupling in Pyrochlore Systems

Pyrochlore systems ($A_{2}B_{2}O_{7}$) with $A$-site rare-earth local moments and $B$-site $5d$ conduction electrons offer excellent material platforms for the discovery of exotic quantum many-body ground states. Notable examples include U(1) quantum spin liquid of the local moments and semimetallic non-Fermi liquid of the conduction electrons. Here we investigate emergent quantum phases and their transitions driven by the Kondo lattice coupling between such highly entangled quantum ground states. Using the renormalization group method, it is shown that weak Kondo lattice coupling is irrelevant, leading to a fractionalized semimetal phase with decoupled local moments and conduction electrons. Upon increasing the Kondo lattice coupling, this phase is unstable to the formation of broken symmetry states. Particularly important is the opposing influence of the Kondo lattice coupling and long-range Coulomb interaction. The former prefers to break the particle-hole symmetry while the latter tends to restore it. The characteristic competition leads to possibly multiple phase transitions, first from a fractionalized semimetal phase to a fractionalized Fermi surface state with particle-hole pockets, followed by the second transition to a fractionalized ferromagnetic state. Multiscale quantum critical behaviors appear at nonzero temperatures and with external magnetic field near such quantum phase transitions. We discuss the implication of these results to the experiments on Pr$_2$Ir$_2$O$_7$.

cond-mat.str-el↗