arXiv subjects

Abhijeet Nayak

Publications and source records attributed to Abhijeet Nayak.

9 recordsLinked to original sources

arXiv2026

What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior

Modern Vision-Language Navigation (VLN) models rely mostly on pre-trained large Vision-Language Models (VLMs) to predict navigation actions. While this fusion of language instructions and visual observations allows multimodal reasoning, it obscures how information is routed across modalities or what mechanisms drive navigation decisions. Thus, it remains unclear whether VLN models ground their predictions in relevant semantic cues or can track task progress. In this work, we study the interpretability and steerability of VLN models. We use intervention-based metrics that measure how visual observations, instructions, and visual memory causally influence navigation decisions. Our results show that these navigation policies are sensitive to all input modalities and do not depend on a single one. We further show that these agents encode navigation progress and retain semantic structure from their VLM backbones, enabling concept-level steering through internal activations. Finally, we extract activation vectors for abstract behaviors to transfer them zero-shot to out-of-distribution real-world scenarios, improving performance without additional fine-tuning.

cs.RO↗

arXiv2026

MetricNet: Recovering Metric Scale in Generative Navigation Policies

Generative navigation policies have made rapid progress in improving end-to-end learned navigation. Despite their promising results, this paradigm has two structural problems. First, the sampled trajectories exist in an abstract, unscaled space without metric grounding. Second, the control strategy discards the full path, instead moving directly towards a single waypoint. This leads to short-sighted and unsafe actions, moving the robot towards obstacles that a complete and correctly scaled path would circumvent. To address these issues, we propose MetricNet, an effective add-on for generative navigation that predicts the metric distance between waypoints, grounding policy outputs in metric coordinates. We evaluate our method in simulation with a new benchmarking framework and show that executing MetricNet-scaled waypoints significantly improves both navigation and exploration performance. Beyond simulation, we further validate our approach in real-world experiments. Finally, we propose MetricNav, which integrates MetricNet into a navigation policy to guide the robot away from obstacles while still moving towards the goal.

cs.RO↗

arXiv2026

Anisotropy, frustration and saddle point in the twisted Kagome antiferromagnet ErPdPb

The kagome lattice, with its inherent geometric frustration, provides a rich platform for exploring intriguing magnetic phenomena and topological electronic structures. In reduced-symmetry structures, such as twisted kagome systems involving rare earth elements, additional anisotropy can arise, enabling intriguing properties including spin-ice states, magnetocaloric effects, noncollinear magnetic ordering, and anomalous Hall effect. Here, we report the synthesis of single crystals of ErPdPb, which features a twisted kagome lattice net of Er atoms within the hexagonal ZrNiAl-type structure, and we investigate its magnetic, electronic, and thermal properties. The material exhibits antiferromagnetic ordering below 2.2 K, consistently observed in magnetic, transport, and heat capacity measurements. Magnetization measurements reveal 1/3 metamagnetic steps along the c-axis below the Néel temperature, suggesting an Ising-spin-like state on the twisted kagome lattice. A pronounced anisotropy between in-plane and out-of-plane resistivity is observed throughout the temperature range of 1.8-300 K, and the compound exhibits a significant frustration index of 13.6 (12.7) along the c-axis (ab-plane). Heat capacity measurements show a broad hump at 2.2 K, with an additional increase below 0.5 K. The anisotropic magnetic properties are further explored through density functional theory (DFT) calculations, which suggest strong easy-axis anisotropy, consistent with experimental magnetic measurements and crystal-field model expectations, and quasi-one-dimensional bands and a spin-split saddle point at the zone center.

cond-mat.str-el↗

arXiv2025

Crystal Growth and Physical Properties of Orthorhombic Kagome Lattice Magnets $R$Fe$_6$Ge$_6$ ($R$=Y, Tb, Dy)

Kagome magnets represent a promising class of materials that exhibit intriguing electronic and magnetic properties, and they have recently garnered significant attention. While most kagome-lattice compounds are hexagonal, we report here single-crystal growth and physical property measurements of $R$Fe$_6$Ge$_6$ ($R$ = Y, Dy, Tb) compounds, which crystallize in an orthorhombic structure. The structure can be derived from a hexagonal prototype $R$Fe$_3$Ge$_2$ by replacing every other $R$ atom with a covalent Ge$_2$ dimer. Ordering of these dimers renders the structure orthorhombic, slightly distorts the kagome net, and makes the three Fe sites formally inequivalent. The iron and rare-earth sublattices order independently. Fe moments order above 400 K, forming ferromagnetic kagome planes stacked antiferromagnetically, while rare-earth moments order below 9 K. TbFe$_6$Ge$_6$ exhibits a single magnetic ordering transition associated with the Tb atoms, whereas DyFe$_6$Ge$_6$ shows two distinct magnetic phase transitions, strongly influenced by crystal electric field effects on the Dy$^{3+}$ ions. Density functional theory (DFT) calculations indicate that the ferromagnetic ordering of the Fe planes is driven by a high density of states at the Fermi energy. They also reveal three dramatically different structural energy scales: $R$ and Ge$_2$ form alternating 1D chains perpendicular to the kagome planes, and violating this alternation incurs a large energy cost. Aligning these chains is less costly, and achieving a two-dimensional order of anti-aligned chains requires very little energy. These compounds represent a unique class of materials, offering new opportunities to investigate the interplay between the distinct crystal lattice geometry and the underlying electronic and magnetic properties.

cond-mat.mtrl-sci↗

arXiv2025

Domain wall induced topological Hall effect in the chiral-lattice ferromagnet Fe$_x$TaS$_2$

Magnetic topology and its associated emergent phenomena are central to realizing intriguing quantum states and spintronics functionalities. Designing spin textures to achieve strong and distinct electrical responses remains a significant challenge. Layered transition metal dichalcogenides offer a versatile platform for tailoring structural and magnetic properties, enabling access to a wide spectrum of topological magnetic states. Here, we report a domain-wall-driven, large, and tunable topological Hall effect (THE) in a non-centrosymmetric intercalated transition metal dichalcogenides series Fe$_x$TaS$_2$. By systematically varying the Fe intercalation level, we exert precise control over the magnetic ground states, allowing manipulation of the topological Hall effect. Real-space magnetic force microscopy (MFM) provides direct evidence of periodic magnetic stripe domain formation, confirming the microscopic origin of the observed topological transport phenomena. Our findings establish a promising way for tuning the topology of domains to generate substantial electromagnetic responses in layered magnetic materials.

cond-mat.mtrl-sci↗

arXiv2025

FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigation

Effective robot navigation in unseen environments is a challenging task that requires precise control actions at high frequencies. Recent advances have framed it as an image-goal-conditioned control problem, where the robot generates navigation actions using frontal RGB images. Current state-of-the-art methods in this area use diffusion policies to generate these control actions. Despite their promising results, these models are computationally expensive and suffer from weak perception. To address these limitations, we present FlowNav, a novel approach that uses a combination of CFM and depth priors from off-the-shelf foundation models to learn action policies for robot navigation. FlowNav is significantly more accurate and faster at navigation and exploration than state-of-the-art methods. We validate our contributions using real robot experiments in multiple environments, demonstrating improved navigation reliability and accuracy. Code and trained models are publicly available.

cs.RO↗

arXiv2024

RaLF: Flow-based Global and Metric Radar Localization in LiDAR Maps

Localization is paramount for autonomous robots. While camera and LiDAR-based approaches have been extensively investigated, they are affected by adverse illumination and weather conditions. Therefore, radar sensors have recently gained attention due to their intrinsic robustness to such conditions. In this paper, we propose RaLF, a novel deep neural network-based approach for localizing radar scans in a LiDAR map of the environment, by jointly learning to address both place recognition and metric localization. RaLF is composed of radar and LiDAR feature encoders, a place recognition head that generates global descriptors, and a metric localization head that predicts the 3-DoF transformation between the radar scan and the map. We tackle the place recognition task by learning a shared embedding space between the two modalities via cross-modal metric learning. Additionally, we perform metric localization by predicting pixel-level flow vectors that align the query radar scan with the LiDAR map. We extensively evaluate our approach on multiple real-world driving datasets and show that RaLF achieves state-of-the-art performance for both place recognition and metric localization. Moreover, we demonstrate that our approach can effectively generalize to different cities and sensor setups than the ones used during training. We make the code and trained models publicly available at http://ralf.cs.uni-freiburg.de.

cs.RO↗

arXiv2024

Altermagnetism in the layered intercalated transition metal dichalcogenide CoNb$_4$Se$_8$

Altermagnets (AMs) are a new class of magnetic materials that combine the beneficial spintronics properties of ferromagnets and antiferromagnets, garnering significant attention recently. Here, we have identified altermagnetism in a layered intercalated transition metal diselenide, CoNb$_4$Se$_8$, which crystallizes with an ordered sublattice of intercalated Co atoms between NbSe$_2$ layers. Single crystals are synthesized, and the structural characterizations are performed using single crystal diffraction and scanning tunneling microscopy. Magnetic measurements reveal easy-axis antiferromagnetism below 168 K. Density functional theory (DFT) calculations indicate that A-type antiferromagnetic ordering with easy-axis spin direction is the ground state, which is verified through single crystal neutron diffraction experiments. Electronic band structure calculations in this magnetic state display spin-split bands, confirming altermagnetism in this compound. The layered structure of CoNb$_4$Se$_8$ presents a promising platform for testing various predicted properties associated with altermagnetism.

cond-mat.str-el↗

arXiv2023

Compositional Servoing by Recombining Demonstrations

Learning-based manipulation policies from image inputs often show weak task transfer capabilities. In contrast, visual servoing methods allow efficient task transfer in high-precision scenarios while requiring only a few demonstrations. In this work, we present a framework that formulates the visual servoing task as graph traversal. Our method not only extends the robustness of visual servoing, but also enables multitask capability based on a few task-specific demonstrations. We construct demonstration graphs by splitting existing demonstrations and recombining them. In order to traverse the demonstration graph in the inference case, we utilize a similarity function that helps select the best demonstration for a specific task. This enables us to compute the shortest path through the graph. Ultimately, we show that recombining demonstrations leads to higher task-respective success. We present extensive simulation and real-world experimental results that demonstrate the efficacy of our approach.

cs.RO↗