Extending Structural Causal Models for Autonomous Embodied Systems

• URL: http://arxiv.org/abs/2406.01384v2
• Date: Wed, 4 Sep 2024 00:10:23 GMT
• Title: Extending Structural Causal Models for Autonomous Embodied Systems
• Authors: Rhys Howard, Lars Kunze,
• Abstract summary: We aim to bridge the divide between autonomous embodied systems and causal reasoning. We first identify the challenges that have limited the integration of structural causal models within such systems. We introduce a number of theoretical extensions to the structural causal model formalism in order to tackle these challenges.
• Score: 5.309950889075669
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work we aim to bridge the divide between autonomous embodied systems and causal reasoning. Autonomous embodied systems have come to increasingly interact with humans, and in many cases may pose risks to the physical or mental well-being of those they interact with. Meanwhile causal models, despite their inherent transparency and ability to offer contrastive explanations, have found limited usage within such systems. As such, we first identify the challenges that have limited the integration of structural causal models within autonomous embodied systems. We then introduce a number of theoretical extensions to the structural causal model formalism in order to tackle these challenges. This augments these models to possess greater levels of modularisation and encapsulation, as well presenting a constant space temporal causal model representation. While not an extension itself, we also prove through the extensions we have introduced that dynamically mutable sets can be captured within structural causal models while maintaining a form of causal stationarity. Finally we introduce two case study architectures demonstrating the application of these extensions along with a discussion of where these extensions could be utilised in future work.

Related papers

• Exploring the Causality of End-to-End Autonomous Driving [57.631400236930375]
  We propose a comprehensive approach to explore and analyze the causality of end-to-end autonomous driving. Our work is the first to unveil the mystery of end-to-end autonomous driving and turn the black box into a white one.
  arXiv  Detail & Related papers  (2024-07-09T04:56:11Z)
• Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks [50.29356570858905]
  We introduce the Dynamical Systems Framework (DSF), which allows a principled investigation of all these architectures in a common representation. We provide principled comparisons between softmax attention and other model classes, discussing the theoretical conditions under which softmax attention can be approximated. This shows the DSF's potential to guide the systematic development of future more efficient and scalable foundation models.
  arXiv  Detail & Related papers  (2024-05-24T17:19:57Z)
• Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art [7.072820266877787]
  We discuss the current use cases of foundation models for decision-making tasks. We argue there is a need to step back and simultaneously design systems that can quantify the certainty of a model's decision.
  arXiv  Detail & Related papers  (2024-03-25T08:11:02Z)
• Can Large Language Models Learn Independent Causal Mechanisms? [9.274428418715347]
  Large Language Models (LLMs) fall short on the same tasks in uncommon settings or with distribution shifts. We show that causal models, that learn abstract variables and causal relationships, can demonstrate increased robustness against changes in the distribution.
  arXiv  Detail & Related papers  (2024-02-04T23:04:02Z)
• Distribution-consistency Structural Causal Models [6.276417011421679]
  We introduce a novel textitdistribution-consistency assumption, and in alignment with it, we propose the Distribution-consistency Structural Causal Models (DiscoSCMs) To concretely reveal the enhanced model capacity, we introduce a new identifiable causal parameter, textitthe probability of consistency, which holds practical significance within DiscoSCM alone.
  arXiv  Detail & Related papers  (2024-01-29T06:46:15Z)
• Targeted Reduction of Causal Models [55.11778726095353]
  Causal Representation Learning offers a promising avenue to uncover interpretable causal patterns in simulations. We introduce Targeted Causal Reduction (TCR), a method for condensing complex intervenable models into a concise set of causal factors. Its ability to generate interpretable high-level explanations from complex models is demonstrated on toy and mechanical systems.
  arXiv  Detail & Related papers  (2023-11-30T15:46:22Z)
• LLM4Drive: A Survey of Large Language Models for Autonomous Driving [62.10344445241105]
  Large language models (LLMs) have demonstrated abilities including understanding context, logical reasoning, and generating answers. In this paper, we systematically review a research line about textitLarge Language Models for Autonomous Driving (LLM4AD).
  arXiv  Detail & Related papers  (2023-11-02T07:23:33Z)
• EqDrive: Efficient Equivariant Motion Forecasting with Multi-Modality for Autonomous Driving [3.4679246185687544]
  We employ EqMotion, a leading equivariant particle, and human prediction model for the task of multi-agent vehicle motion forecasting. By leveraging EqMotion, our model achieves state-of-the-art (SOTA) performance with fewer parameters (1.2 million) and a significantly reduced training time (less than 2 hours)
  arXiv  Detail & Related papers  (2023-10-26T16:32:34Z)
• Towards Probabilistic Causal Discovery, Inference & Explanations for Autonomous Drones in Mine Surveying Tasks [5.569226615350014]
  Causal modelling can aid autonomous agents in making decisions and explaining outcomes. Here we identify challenges relating to causality in the context of a drone system operating in a salt mine. We propose a probabilistic causal framework consisting of: causally-informed POMDP planning, online SCM adaptation, and post-hoc counterfactual explanations.
  arXiv  Detail & Related papers  (2023-08-19T15:12:55Z)
• Model-Based Reinforcement Learning with Isolated Imaginations [61.67183143982074]
  We propose Iso-Dream++, a model-based reinforcement learning approach. We perform policy optimization based on the decoupled latent imaginations. This enables long-horizon visuomotor control tasks to benefit from isolating mixed dynamics sources in the wild.
  arXiv  Detail & Related papers  (2023-03-27T02:55:56Z)
• Modular Deep Learning [120.36599591042908]
  Transfer learning has recently become the dominant paradigm of machine learning. It remains unclear how to develop models that specialise towards multiple tasks without incurring negative interference. Modular deep learning has emerged as a promising solution to these challenges.
  arXiv  Detail & Related papers  (2023-02-22T18:11:25Z)
• Leveraging the structure of dynamical systems for data-driven modeling [111.45324708884813]
  We consider the impact of the training set and its structure on the quality of the long-term prediction. We show how an informed design of the training set, based on invariants of the system and the structure of the underlying attractor, significantly improves the resulting models.
  arXiv  Detail & Related papers  (2021-12-15T20:09:20Z)
• A Utility Maximization Model of Pedestrian and Driver Interactions [5.02231401459109]
  We develop a modeling framework applying the principles of utility, motor primitives, and intermittent action decisions to account for the details of interactive behaviors among road users. We show that these phenomena emerge naturally from our modeling framework when the model can evolve its parameters as a consequence of the situations.
  arXiv  Detail & Related papers  (2021-10-21T09:42:02Z)
• CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning [68.74447489372037]
  We present a high-fidelity simulation environment that is designed for developing algorithms for causal discovery and counterfactual reasoning. A core component of our work is to introduce textitagency, such that it is simple to define and create complex scenarios. We perform experiments with three state-of-the-art methods to create baselines and highlight the affordances of this environment.
  arXiv  Detail & Related papers  (2021-06-25T00:21:41Z)
• Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA [4.340954888479091]
  We introduce a new general identifiable framework for principled disentanglement referred to as Structured Independent Component Analysis (SNICA) Our contribution is to extend the identifiability theory of deep generative models for a very broad class of structured models. We establish the major result that identifiability for this framework holds even in the presence of noise of unknown distribution.
  arXiv  Detail & Related papers  (2021-06-17T15:56:57Z)
• Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving [47.22329993674051]
  We aim to develop an explainable model that generates explanations consistent with both human domain knowledge and the model's inherent causal relation. In particular, we focus on an essential building block of autonomous driving, multi-agent interaction modeling. We demonstrate that it can model interactive traffic scenarios under both simulation and real-world settings.
  arXiv  Detail & Related papers  (2021-02-23T19:34:32Z)
• Self-consistent theory of mobility edges in quasiperiodic chains [62.997667081978825]
  We introduce a self-consistent theory of mobility edges in nearest-neighbour tight-binding chains with quasiperiodic potentials. mobility edges are generic in quasiperiodic systems which lack the energy-independent self-duality of the commonly studied Aubry-Andr'e-Harper model.
  arXiv  Detail & Related papers  (2020-12-02T19:00:09Z)
• Multi-agent Trajectory Prediction with Fuzzy Query Attention [15.12743751614964]
  Trajectory prediction for scenes with multiple agents is a challenging problem in numerous domains such as traffic prediction, pedestrian tracking and path planning. We present a general architecture to address this challenge which models the crucial inductive biases of motion, namely, inertia, relative motion, intents and interactions.
  arXiv  Detail & Related papers  (2020-10-29T19:12:12Z)
• S2RMs: Spatially Structured Recurrent Modules [105.0377129434636]
  We take a step towards exploiting dynamic structure that are capable of simultaneously exploiting both modular andtemporal structures. We find our models to be robust to the number of available views and better capable of generalization to novel tasks without additional training.
  arXiv  Detail & Related papers  (2020-07-13T17:44:30Z)

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.