Model-free reinforcement learning (RL) is a powerful tool to learn a broad range of robot skills and policies. However, a lack of policy interpretability can inhibit their successful deployment in downstream applications, particularly when differences in environmental conditions may result in unpredictable behaviour or generalisation failures. As a result, there has been a growing emphasis in machine learning around the inclusion of stronger inductive biases in models to improve generalisation. This paper proposes an alternative strategy, inverse value estimation for interpretable policy certificates (IV-Posterior), which seeks to identify the inductive biases or idealised conditions of operation already held by pre-trained policies, and then use this information to guide their deployment. IV-Posterior uses MaskedAutoregressive Flows to fit distributions over the set of conditions or environmental parameters in which a policy is likely to be effective. This distribution can then be used as a policy certificate in downstream applications. We illustrate the use of IV-Posterior across a two environments, and show that substantial performance gains can be obtained when policy selection incorporates knowledge of the inductive biases that these policies hold.
Contacts and friction are inherent to nearly all robotic manipulation tasks. Through the motor skill of insertion, we study how robots can learn to cope when these attributes play a salient role. In this work we propose residual learning from demonstration (rLfD), a framework that combines dynamic movement primitives (DMP) that rely on behavioural cloning with a reinforcement learning (RL) based residual correction policy. The proposed solution is applied directly in task space and operates on the full pose of the robot. We show that rLfD outperforms alternatives and improves the generalisation abilities of DMPs. We evaluate this approach by training an agent to successfully perform both simulated and real world insertions of pegs, gears and plugs into respective sockets.
Humans can easily reason about the sequence of high level actions needed to complete tasks, but it is particularly difficult to instil this ability in robots trained from relatively few examples. This work considers the task of neural action sequencing conditioned on a single reference visual state. This task is extremely challenging as it is not only subject to the significant combinatorial complexity that arises from large action sets, but also requires a model that can perform some form of symbol grounding, mapping high dimensional input data to actions, while reasoning about action relationships. Drawing on human cognitive abilities to rearrange objects in scenes to create new configurations, we take a permutation perspective and argue that action sequencing benefits from the ability to reason about both permutations and ordering concepts. Empirical analysis shows that neural models trained with latent permutations outperform standard neural architectures in constrained action sequencing tasks. Results also show that action sequencing using visual permutations is an effective mechanism to initialise and speed up traditional planning techniques and successfully scales to far greater action set sizes than models considered previously.
Learning low-dimensional latent state space dynamics models has been a powerful paradigm for enabling vision-based planning and learning for control. We introduce a latent dynamics learning framework that is uniquely designed to induce proportional controlability in the latent space, thus enabling the use of much simpler controllers than prior work. We show that our learned dynamics model enables proportional control from pixels, dramatically simplifies and accelerates behavioural cloning of vision-based controllers, and provides interpretable goal discovery when applied to imitation learning of switching controllers from demonstration.
This paper addresses a common class of problems where a robot learns to perform a discovery task based on example solutions, or human demonstrations. For example consider the problem of ultrasound scanning, where the demonstration requires that an expert adaptively searches for a satisfactory view of internal organs, vessels or tissue and potential anomalies while maintaining optimal contact between the probe and surface tissue. Such problems are currently solved by inferring notional rewards that, when optimised for, result in a plan that mimics demonstrations. A pivotal assumption, that plans with higher reward should be exponentially more likely, leads to the de facto approach for reward inference in robotics. While this approach of maximum entropy inverse reinforcement learning leads to a general and elegant formulation, it struggles to cope with frequently encountered sub-optimal demonstrations. In this paper, we propose an alternative approach to cope with the class of problems where sub-optimal demonstrations occur frequently. We hypothesise that, in tasks which require discovery, successive states of any demonstration are progressively more likely to be associated with a higher reward. We formalise this temporal ranking approach and show that it improves upon maximum-entropy approaches to perform reward inference for autonomous ultrasound scanning, a novel application of learning from demonstration in medical imaging.
Saliency maps are often used in computer vision to provide intuitive interpretations of what input regions a model has used to produce a specific prediction. A number of approaches to saliency map generation are available, but most require access to model parameters. This work proposes an approach for saliency map generation for black-box models, where no access to model parameters is available, using a Bayesian optimisation sampling method. The approach aims to find the global salient image region responsible for a particular (black-box) model's prediction. This is achieved by a sampling-based approach to model perturbations that seeks to localise salient regions of an image to the black-box model. Results show that the proposed approach to saliency map generation outperforms grid-based perturbation approaches, and performs similarly to gradient-based approaches which require access to model parameters.
Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a model of the environment to aid motion prediction of tracked agents. This paper shows that modelling the spatial and dynamic aspects of a given environment alongside the local per agent behaviour results in more accurate and informed long-term motion prediction. Further, we observe that this decoupling of dynamics and environment models allows for better adaptation to unseen environments, requiring that only a spatial representation of a new environment be learned. We highlight the model's prediction capability using a benchmark pedestrian tracking problem and by tracking a robot arm performing a tabletop manipulation task. The proposed approach allows for robust and data efficient forward modelling, and relaxes the need for full model re-training in new environments. We evaluate this through an ablation study which shows better performance gain when utilising both representation modules in addition to improved generalisation on tasks with dynamics unseen at training time.
Datasets are crucial when training a deep neural network. When datasets are unrepresentative, trained models are prone to bias because they are unable to generalise to real world settings. This is particularly problematic for models trained in specific cultural contexts, which may not represent a wide range of races, and thus fail to generalise. This is a particular challenge for Driver drowsiness detection, where many publicly available datasets are unrepresentative as they cover only certain ethnicity groups. Traditional augmentation methods are unable to improve a model's performance when tested on other groups with different facial attributes, and it is often challenging to build new, more representative datasets. In this paper, we introduce a novel framework that boosts the performance of detection of drowsiness for different ethnicity groups. Our framework improves Convolutional Neural Network (CNN) trained for prediction by using Generative Adversarial networks (GAN) for targeted data augmentation based on a population bias visualisation strategy that groups faces with similar facial attributes and highlights where the model is failing. A sampling method selects faces where the model is not performing well, which are used to fine-tune the CNN. Experiments show the efficacy of our approach in improving driver drowsiness detection for under represented ethnicity groups. Here, models trained on publicly available datasets are compared with a model trained using the proposed data augmentation strategy. Although developed in the context of driver drowsiness detection, the proposed framework is not limited to the driver drowsiness detection task, but can be applied to other applications.
Context plays a significant role in the generation of motion for dynamic agents in interactive environments. This work proposes a modular method that utilises a model of the environment to aid motion prediction of tracked agents. This paper shows that modelling the spatial and dynamic aspects of a given environment alongside the local per agent behaviour results in more accurate and informed long-term motion prediction. Further, we observe that this decoupling of dynamics and environment models allows for better generalisation to unseen environments, requiring that only a spatial representation of a new environment be learned. We highlight the model's prediction capability using a benchmark pedestrian tracking problem and by tracking a robot arm performing a tabletop manipulation task. The proposed approach allows for robust and data efficient forward modelling, and relaxes the need for full model re-training in new environments. We evaluate this through an ablation study which shows better performance gain when decoupling representation modules in addition to improved generalisation on tasks with dynamics unseen at training time.
Precision cutting of soft-tissue remains a challenging problem in robotics, due to the complex and unpredictable mechanical behaviour of tissue under manipulation. Here, we consider the challenge of cutting along the boundary between two soft mediums, a problem that is made extremely difficult due to visibility constraints, which means that the precise location of the cutting trajectory is typically unknown. This paper introduces a novel strategy to address this task, using a binary medium classifier trained using joint torque measurements, and a closed loop control law that relies on an error signal compactly encoded in the decision boundary of the classifier. We illustrate this on a grapefruit cutting task, successfully modulating a nominal trajectory fit using dynamic movement primitives to follow the boundary between grapefruit pulp and peel using torque based medium classification. Results show that this control strategy is successful in 72 % of attempts in contrast to control using a nominal trajectory, which only succeeds in 50 % of attempts.