In this document we provide additional details and experiments.

In safe reinforcement learning (RL), auxiliary safety costs are used to align the agent to safe decision making. In practice, safety constraints, including cost functions and budgets, are unknown or hard to specify, as it requires anticipation of all possible unsafe behaviors. We therefore address a general setting where the true safety definition is unknown, and has to be learned from sparsely labeled data. Our key contributions are: first, we design a safety model that performs credit assignment to estimate each decision step's impact on the overall safety using a dataset of diverse trajectories and their corresponding binary safety labels (i.e., whether the corresponding trajectory is safe/unsafe). Second, we illustrate the architecture of our safety model to demonstrate its ability to learn a separate safety score for each timestep. Third, we reformulate the safe RL problem using the proposed safety model and derive an effective algorithm to optimize a safe yet rewarding policy. Finally, our empirical results corroborate our findings and show that this approach is effective in satisfying unknown safety definition, and scalable to various continuous control tasks.

In a multi-modal system which combines thruster and legged locomotion such our state-of-the-art Harpy platform to perform dynamic locomotion. Therefore, it is very important to have a proper estimate of Thruster force. Harpy is a bipedal robot capable of legged-aerial locomotion using its legs and thrusters attached to its main frame. we can characterize thruster force using a thrust stand but it generally does not account for working conditions such as battery voltage. In this study, we present a momentum-based thruster force estimator. One of the key information required to estimate is terrain information. we show estimation results with and without terrain knowledge. In this work, we derive a conjugate momentum thruster force estimator and implement it on a numerical simulator that uses thruster force to perform thruster-assisted walking.

Formulating an effective constraint model of a parameterised problem class is crucial to the efficiency with which instances of the class can subsequently be solved. It is difficult to know beforehand which of a set of candidate models will perform best in practice. This paper presents a system that employs graph rewriting to reformulate an input model for improved performance automatically. By situating our work in the Essence abstract constraint specification language, we can use the structure in its high level variable types to trigger rewrites directly. We implement our system via rewrite rules expressed in the Graph Programs 2 language, applied to the abstract syntax tree of an input specification. We show how to automatically translate the solution of the reformulated problem into a solution of the original problem for verification and presentation. We demonstrate the efficacy of our system with a detailed case study.

Constraint modelling languages such as Essence offer a means to describe combinatorial problems at a high-level, i.e., without committing to detailed modelling decisions for a particular solver or solving paradigm. Given a problem description written in Essence, there are multiple ways to translate it to a low-level constraint model. Choosing the right combination of a low-level constraint model and a target constraint solver can have significant impact on the effectiveness of the solving process. Furthermore, the choice of the best combination of constraint model and solver can be instance-dependent, i.e., there may not exist a single combination that works best for all instances of the same problem. In this paper, we consider the task of building machine learning models to automatically select the best combination for a problem instance. A critical part of the learning process is to define instance features, which serve as input to the selection model. Our contribution is automatic learning of instance features directly from the high-level representation of a problem instance using a language model. We evaluate the performance of our approach using the Essence modelling language with a case study involving the car sequencing problem.

Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to divide and distribute the subtasks between the participating agents to carry out the main task. In contrast, we propose to learn a human constraints model that, in addition, considers the diverse behaviors of different human operators. We consider a type of collaboration in a shared-autonomy fashion, where both a human operator and an assistive robot act simultaneously in the same task space that affects each other's actions. The task of the assistive agent is to augment the skill of humans to perform a shared task by supporting humans as much as possible, both in terms of reducing the workload and minimizing the discomfort for the human operator. Therefore, we propose an augmentative assistant agent capable of learning and adapting to human physical constraints, aligning its actions with the ergonomic preferences and limitations of the human operator.

It is well established that formulating an effective constraint model of a problem of interest is crucial to the efficiency with which it can subsequently be solved. Following from the observation that it is difficult, if not impossible, to know a priori which of a set of candidate models will perform best in practice, we envisage a system that explores the space of models through a process of reformulation from an initial model, guided by performance on a set of training instances from the problem class under consideration. We plan to situate this system in a refinement-based approach, where a user writes a constraint specification describing a problem above the level of abstraction at which many modelling decisions are made. In this position paper we set out our plan for an exploratory reformulation system, and discuss progress made so far.

We report on progress in modelling and solving Puzznic, a video game requiring the player to plan sequences of moves to clear a grid by matching blocks. We focus here on levels with no moving blocks. We compare a planning approach and three constraint programming approaches on a small set of benchmark instances. The planning approach is at present superior to the constraint programming approaches, but we outline proposals for improving the constraint models.

The Essence language allows a user to specify a constraint problem at a level of abstraction above that at which constraint modelling decisions are made. Essence specifications are refined into constraint models using the Conjure automated modelling tool, which employs a suite of refinement rules. However, Essence is a rich language in which there are many equivalent ways to specify a given problem. A user may therefore omit the use of domain attributes or abstract types, resulting in fewer refinement rules being applicable and therefore a reduced set of output models from which to select. This paper addresses the problem of recovering this information automatically to increase the robustness of the quality of the output constraint models in the face of variation in the input Essence specification. We present reformulation rules that can change the type of a decision variable or add attributes that shrink its domain. We demonstrate the efficacy of this approach in terms of the quantity and quality of models Conjure can produce from the transformed specification compared with the original.