Semantic-Metric Bayesian Risk Fields: Learning Robot Safety from Human Videos with a VLM Prior

• URL: http://arxiv.org/abs/2512.08233v1
• Date: Tue, 09 Dec 2025 04:19:58 GMT
• Title: Semantic-Metric Bayesian Risk Fields: Learning Robot Safety from Human Videos with a VLM Prior
• Abstract summary: Humans interpret safety not as a binary signal but as a continuous, context- and spatially-dependent notion of risk.<n>This work proposes a framework for extracting implicit human risk models supervised directly from safe human demonstration videos and VLM common sense.
• Score: 10.193047117743221
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans interpret safety not as a binary signal but as a continuous, context- and spatially-dependent notion of risk. While risk is subjective, humans form rational mental models that guide action selection in dynamic environments. This work proposes a framework for extracting implicit human risk models by introducing a novel, semantically-conditioned and spatially-varying parametrization of risk, supervised directly from safe human demonstration videos and VLM common sense. Notably, we define risk through a Bayesian formulation. The prior is furnished by a pretrained vision-language model. In order to encourage the risk estimate to be more human aligned, a likelihood function modulates the prior to produce a relative metric of risk. Specifically, the likelihood is a learned ViT that maps pretrained features, to pixel-aligned risk values. Our pipeline ingests RGB images and a query object string, producing pixel-dense risk images. These images that can then be used as value-predictors in robot planning tasks or be projected into 3D for use in conventional trajectory optimization to produce human-like motion. This learned mapping enables generalization to novel objects and contexts, and has the potential to scale to much larger training datasets. In particular, the Bayesian framework that is introduced enables fast adaptation of our model to additional observations or common sense rules. We demonstrate that our proposed framework produces contextual risk that aligns with human preferences. Additionally, we illustrate several downstream applications of the model; as a value learner for visuomotor planners or in conjunction with a classical trajectory optimization algorithm. Our results suggest that our framework is a significant step toward enabling autonomous systems to internalize human-like risk. Code and results can be found at https://riskbayesian.github.io/bayesian_risk/.

Related papers

• Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models [10.47361214312137]
  We introduce DROPJ, a human-centred method for both safe training and deployment.<n>We first learn a world model (a learned simulator) from a dataset of prior real-world trajectories.<n>A human then plays the game in this learned simulator to extract several informative simulated trajectories.<n>We then train a reward model from these justified preferences and use it, together with the world model, to directly deploy the agent.
  arXiv  Detail & Related papers  (2026-07-14T18:22:14Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• Context-Aware Risk Estimation in Home Environments: A Probabilistic Framework for Service Robots [2.5695499302569327]
  We present a novel framework for estimating accident-prone regions in everyday indoor scenes, aimed at improving real-time risk awareness in service robots.<n>Our approach models object-level risk and context through a semantic graph-based propagation algorithm.<n>Our method is validated on a dataset with human-annotated risk regions, achieving a binary risk detection accuracy of 75%.
  arXiv  Detail & Related papers  (2025-08-27T11:14:05Z)
• Risk-aware Direct Preference Optimization under Nested Risk Measure [23.336246526648374]
  Risk-aware Direct Preference Optimization (Ra-DPO) is a novel approach that incorporates risk-awareness by employing a class of nested risk measures.<n> Experimental results across three open-source datasets demonstrate the proposed method's superior performance in balancing alignment performance and model drift.
  arXiv  Detail & Related papers  (2025-05-26T08:01:37Z)
• Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models! [52.0855711767075]
  EvoSeed is an evolutionary strategy-based algorithmic framework for generating photo-realistic natural adversarial samples. We employ CMA-ES to optimize the search for an initial seed vector, which, when processed by the Conditional Diffusion Model, results in the natural adversarial sample misclassified by the Model. Experiments show that generated adversarial images are of high image quality, raising concerns about generating harmful content bypassing safety classifiers.
  arXiv  Detail & Related papers  (2024-02-07T09:39:29Z)
• Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning [12.156082576280955]
  Deployment in hazardous environments requires robots to understand the risks associated with their actions and movements to prevent accidents. We propose a risk sensitive locomotion training method employing distributional reinforcement learning to consider safety explicitly. We show emergent risk sensitive locomotion behavior in simulation and on the quadrupedal robot ANYmal.
  arXiv  Detail & Related papers  (2023-09-25T16:05:32Z)
• Adaptive Risk Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning [17.940958199767234]
  We present a distributional reinforcement learning framework to learn adaptive risk tendency policies. We show our algorithm can adjust its risk-sensitivity on the fly both in simulation and real-world experiments.
  arXiv  Detail & Related papers  (2022-03-28T13:39:58Z)
• Attribute-Guided Adversarial Training for Robustness to Natural Perturbations [64.35805267250682]
  We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
  arXiv  Detail & Related papers  (2020-12-03T10:17:30Z)
• Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction [55.569050872780224]
  We present an online framework for safe crowd-robot interaction based on risk-sensitive optimal control, wherein the risk is modeled by the entropic risk measure. Our modular approach decouples the crowd-robot interaction into learning-based prediction and model-based control. A simulation study and a real-world experiment show that the proposed framework can accomplish safe and efficient navigation while avoiding collisions with more than 50 humans in the scene.
  arXiv  Detail & Related papers  (2020-09-12T02:02:52Z)
• Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance [95.86944752753564]
  We propose an online path planning architecture that extends the model predictive control (MPC) formulation to consider future location uncertainties. Our algorithm combines an object detection pipeline with a recurrent neural network (RNN) which infers the covariance of state estimates. The robustness of our methods is validated on complex quadruped robot dynamics and can be generally applied to most robotic platforms.
  arXiv  Detail & Related papers  (2020-07-28T07:34:30Z)
• Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning [75.56839075060819]
  Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sample-inefficient and brittle. In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline.
  arXiv  Detail & Related papers  (2020-05-21T19:47:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.