Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract)

Dynamic Bayesian networks (DBNs) are a general model for stochastic processes with partially observed states. Belief filtering in DBNs is the task of inferring the belief state (i.e. the probability distribution over process states) based on incomplete and uncertain observations. In this article, we explore the idea of accelerating the filtering task by automatically exploiting causality in the process. We consider a specific type of causal relation, called passivity, which pertains to how state variables cause changes in other variables. We present the Passivity-based Selective Belief Filtering (PSBF) method, which maintains a factored belief representation and exploits passivity to perform selective updates over the belief factors. PSBF is evaluated in both synthetic processes and a simulated multi-robot warehouse, where it outperformed alternative filtering methods by exploiting passivity.

Hybrid system identification using switching density networks

Behaviour cloning is a commonly used strategy for imitation learning and can be extremely effective in constrained domains. However, in cases where the dynamics of an environment may be state dependent and varying, behaviour cloning places a burden on model capacity and the number of demonstrations required. This paper introduces switching density networks, which rely on a categorical reparametrisation for hybrid system identification. This results in a network comprising a classification layer that is followed by a regression layer. We use switching density networks to predict the parameters of hybrid control laws, which are toggled by a switching layer to produce different controller outputs, when conditioned on an input state. This work shows how switching density networks can be used for hybrid system identification in a variety of tasks, successfully identifying the key joint angle goals that make up manipulation tasks, while simultaneously learning image-based goal classifiers and regression networks that predict joint angles from images. We also show that they can cluster the phase space of an inverted pendulum, identifying the balance, spin and pump controllers required to solve this task. Switching density networks can be difficult to train, but we introduce a cross entropy regularisation loss that stabilises training.

DynoPlan: Combining Motion Planning and Deep Neural Network based Controllers for Safe HRL

Many realistic robotics tasks are best solved compositionally, through control architectures that sequentially invoke primitives and achieve error correction through the use of loops and conditionals taking the system back to alternative earlier states. Recent end-to-end approaches to task learning attempt to directly learn a single controller that solves an entire task, but this has been difficult for complex control tasks that would have otherwise required a diversity of local primitive moves, and the resulting solutions are also not easy to inspect for plan monitoring purposes. In this work, we aim to bridge the gap between hand designed and learned controllers, by representing each as an option in a hybrid hierarchical Reinforcement Learning framework - DynoPlan. We extend the options framework by adding a dynamics model and the use of a nearness-to-goal heuristic, derived from demonstrations. This translates the optimization of a hierarchical policy controller to a problem of planning with a model predictive controller. By unrolling the dynamics of each option and assessing the expected value of each future state, we can create a simple switching controller for choosing the optimal policy within a constrained time horizon similarly to hill climbing heuristic search. The individual dynamics model allows each option to iterate and be activated independently of the specific underlying instantiation, thus allowing for a mix of motion planning and deep neural network based primitives. We can assess the safety regions of the resulting hybrid controller by investigating the initiation sets of the different options, and also by reasoning about the completeness and performance guarantees of the underpinning motion planners.

Learning Grasp Affordance Reasoning through Semantic Relations

Reasoning about object affordances allows an autonomous agent to perform generalised manipulation tasks among object instances. While current approaches to grasp affordance estimation are effective, they are limited to a single hypothesis. We present an approach for detection and extraction of multiple grasp affordances on an object via visual input. We define semantics as a combination of multiple attributes, which yields benefits in terms of generalisation for grasp affordance prediction. We use Markov Logic Networks to build a knowledge base graph representation to obtain a probability distribution of grasp affordances for an object. To harvest the knowledge base, we collect and make available a novel dataset that relates different semantic attributes. We achieve reliable mappings of the predicted grasp affordances on the object by learning prototypical grasping patches from several examples. We show our method's generalisation capabilities on grasp affordance prediction for novel instances and compare with similar methods in the literature. Moreover, using a robotic platform, on simulated and real scenarios, we evaluate the success of the grasping task when conditioned on the grasp affordance prediction.

Iterative Model-Based Reinforcement Learning Using Simulations in the Differentiable Neural Computer

We propose a lifelong learning architecture, the Neural Computer Agent (NCA), where a Reinforcement Learning agent is paired with a predictive model of the environment learned by a Differentiable Neural Computer (DNC). The agent and DNC model are trained in conjunction iteratively. The agent improves its policy in simulations generated by the DNC model and rolls out the policy to the live environment, collecting experiences in new portions or tasks of the environment for further learning. Experiments in two synthetic environments show that DNC models can continually learn from pixels alone to simulate new tasks as they are encountered by the agent, while the agents can be successfully trained to solve the tasks using Proximal Policy Optimization entirely in simulations.

Reasoning on Grasp-Action Affordances

Artificial intelligence is essential to succeed in challenging activities that involve dynamic environments, such as object manipulation tasks in indoor scenes. Most of the state-of-the-art literature explores robotic grasping methods by focusing exclusively on attributes of the target object. When it comes to human perceptual learning approaches, these physical qualities are not only inferred from the object, but also from the characteristics of the surroundings. This work proposes a method that includes environmental context to reason on an object affordance to then deduce its grasping regions. This affordance is reasoned using a ranked association of visual semantic attributes harvested in a knowledge base graph representation. The framework is assessed using standard learning evaluation metrics and the zero-shot affordance prediction scenario. The resulting grasping areas are compared with unseen labelled data to asses their accuracy matching percentage. The outcome of this evaluation suggest the autonomy capabilities of the proposed method for object interaction applications in indoor environments.

An Empirical Evaluation of Adversarial Robustness under Transfer Learning

In this work, we evaluate adversarial robustness in the context of transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10. Specifically, we study the effects of using robust optimisation in the source and target networks. This allows us to identify transfer learning strategies under which adversarial defences are successfully retained, in addition to revealing potential vulnerabilities. We study the extent to which features learnt by a fast gradient sign method (FGSM) and its iterative alternative (PGD) can preserve their defence properties against black and white-box attacks under three different transfer learning strategies. We find that using PGD examples during training on the source task leads to more general robust features that are easier to transfer. Furthermore, under successful transfer, it achieves 5.2% more accuracy against white-box PGD attacks than suitable baselines. Overall, our empirical evaluations give insights on how well adversarial robustness under transfer learning can generalise.

Towards Evaluating and Understanding Robust Optimisation under Transfer

This work evaluates the efficacy of adversarial robustness under transfer from CIFAR 100 to CIFAR 10. This allows us to identify transfer learning strategies under which adversarial defences are successfully retained, in addition to revealing potential vulnerabilities. We study the extent to which features crafted by fast gradient sign methods (FGSM) and their iterative alternative (PGD) can preserve their defence properties against black and white-box attacks under three different transfer learning strategies. We find that using PGD examples during training leads to more general robustness that is easier to transfer. Furthermore, under successful transfer, it achieves 5.2% more accuracy against white-box PGD attacks than the considered baselines. In this paper, we study the effects of using robust optimisation in the source and target networks. Our empirical evaluation sheds light on how well such mechanisms generalise while achieving comparable results to non-transferred defences.

Learning Programmatically Structured Representations with Perceptor Gradients

We present the perceptor gradients algorithm -- a novel approach to learning symbolic representations based on the idea of decomposing an agent's policy into i) a perceptor network extracting symbols from raw observation data and ii) a task encoding program which maps the input symbols to output actions. We show that the proposed algorithm is able to learn representations that can be directly fed into a Linear-Quadratic Regulator (LQR) or a general purpose A* planner. Our experimental results confirm that the perceptor gradients algorithm is able to efficiently learn transferable symbolic representations as well as generate new observations according to a semantically meaningful specification.

To Stir or Not to Stir: Online Estimation of Liquid Properties for Pouring Actions

Our brains are able to exploit coarse physical models of fluids to solve everyday manipulation tasks. There has been considerable interest in developing such a capability in robots so that they can autonomously manipulate fluids adapting to different conditions. In this paper, we investigate the problem of adaptation to liquids with different characteristics. We develop a simple calibration task (stirring with a stick) that enables rapid inference of the parameters of the liquid from RBG data. We perform the inference in the space of simulation parameters rather than on physically accurate parameters. This facilitates prediction and optimization tasks since the inferred parameters may be fed directly to the simulator. We demonstrate that our "stirring" learner performs better than when the robot is calibrated with pouring actions. We show that our method is able to infer properties of three different liquids -- water, glycerin and gel -- and present experimental results by executing stirring and pouring actions on a UR10. We believe that decoupling of the training actions from the goal task is an important step towards simple, autonomous learning of the behavior of different fluids in unstructured environments.