Recent methods using Reinforcement Learning (RL) have proven to be successful for training intelligent agents in unknown environments. However, RL has not been applied widely in real-world robotics scenarios. This is because current state-of-the-art RL methods require large amounts of data to learn a specific task, leading to unreasonable costs when deploying the agent to collect data in real-world applications. In this paper, we build from existing work that reshapes the reward function in RL by introducing a Control Lyapunov Function (CLF), which is demonstrated to reduce the sample complexity. Still, this formulation requires knowing a CLF of the system, but due to the lack of a general method, it is often a challenge to identify a suitable CLF. Existing work can compute low-dimensional CLFs via a Hamilton-Jacobi reachability procedure. However, this class of methods becomes intractable on high-dimensional systems, a problem that we address by using a system decomposition technique to compute what we call Decomposed Control Lyapunov Functions (DCLFs). We use the computed DCLF for reward shaping, which we show improves RL performance. Through multiple examples, we demonstrate the effectiveness of this approach, where our method finds a policy to successfully land a quadcopter in less than half the amount of real-world data required by the state-of-the-art Soft-Actor Critic algorithm.
When multiple agents interact in a common environment, each agent's actions impact others' future decisions, and noncooperative dynamic games naturally capture this coupling. In interactive motion planning, however, agents typically do not have access to a complete model of the game, e.g., due to unknown objectives of other players. Therefore, we consider the inverse game problem, in which some properties of the game are unknown a priori and must be inferred from observations. Existing maximum likelihood estimation (MLE) approaches to solve inverse games provide only point estimates of unknown parameters without quantifying uncertainty, and perform poorly when many parameter values explain the observed behavior. To address these limitations, we take a Bayesian perspective and construct posterior distributions of game parameters. To render inference tractable, we employ a variational autoencoder (VAE) with an embedded differentiable game solver. This structured VAE can be trained from an unlabeled dataset of observed interactions, naturally handles continuous, multi-modal distributions, and supports efficient sampling from the inferred posteriors without computing game solutions at runtime. Extensive evaluations in simulated driving scenarios demonstrate that the proposed approach successfully learns the prior and posterior objective distributions, provides more accurate objective estimates than MLE baselines, and facilitates safer and more efficient game-theoretic motion planning.
One of the fundamental challenges associated with reinforcement learning (RL) is that collecting sufficient data can be both time-consuming and expensive. In this paper, we formalize a concept of time reversal symmetry in a Markov decision process (MDP), which builds upon the established structure of dynamically reversible Markov chains (DRMCs) and time-reversibility in classical physics. Specifically, we investigate the utility of this concept in reducing the sample complexity of reinforcement learning. We observe that utilizing the structure of time reversal in an MDP allows every environment transition experienced by an agent to be transformed into a feasible reverse-time transition, effectively doubling the number of experiences in the environment. To test the usefulness of this newly synthesized data, we develop a novel approach called time symmetric data augmentation (TSDA) and investigate its application in both proprioceptive and pixel-based state within the realm of off-policy, model-free RL. Empirical evaluations showcase how these synthetic transitions can enhance the sample efficiency of RL agents in time reversible scenarios without friction or contact. We also test this method in more realistic environments where these assumptions are not globally satisfied. We find that TSDA can significantly degrade sample efficiency and policy performance, but can also improve sample efficiency under the right conditions. Ultimately we conclude that time symmetry shows promise in enhancing the sample efficiency of reinforcement learning and provide guidance when the environment and reward structures are of an appropriate form for TSDA to be employed effectively.
A core challenge of multi-robot interactions is collision avoidance among robots with potentially conflicting objectives. We propose a game-theoretic method for collision avoidance based on rotating hyperplane constraints. These constraints ensure collision avoidance by defining separating hyperplanes that rotate around a keep-out zone centered on certain robots. Since it is challenging to select the parameters that define a hyperplane without introducing infeasibilities, we propose to learn them from an expert trajectory i.e., one collected by recording human operators. To do so, we solve for the parameters whose corresponding equilibrium trajectory best matches the expert trajectory. We validate our method by learning hyperplane parameters from noisy expert trajectories and demonstrate the generalizability of the learned parameters to scenarios with more robots and previously unseen initial conditions.
When interacting with other non-competitive decision-making agents, it is critical for an autonomous agent to have inferable behavior: Their actions must convey their intention and strategy. For example, an autonomous car's strategy must be inferable by the pedestrians interacting with the car. We model the inferability problem using a repeated bimatrix Stackelberg game with observations where a leader and a follower repeatedly interact. During the interactions, the leader uses a fixed, potentially mixed strategy. The follower, on the other hand, does not know the leader's strategy and dynamically reacts based on observations that are the leader's previous actions. In the setting with observations, the leader may suffer from an inferability loss, i.e., the performance compared to the setting where the follower has perfect information of the leader's strategy. We show that the inferability loss is upper-bounded by a function of the number of interactions and the stochasticity level of the leader's strategy, encouraging the use of inferable strategies with lower stochasticity levels. As a converse result, we also provide a game where the required number of interactions is lower bounded by a function of the desired inferability loss.
In this paper, we consider the problem of discovering dynamical system models from noisy data. The presence of noise is known to be a significant problem for symbolic regression algorithms. We combine Gaussian process regression, a nonparametric learning method, with SINDy, a parametric learning approach, to identify nonlinear dynamical systems from data. The key advantages of our proposed approach are its simplicity coupled with the fact that it demonstrates improved robustness properties with noisy data over SINDy. We demonstrate our proposed approach on a Lotka-Volterra model and a unicycle dynamic model in simulation and on an NVIDIA JetRacer system using hardware data. We demonstrate improved performance over SINDy for discovering the system dynamics and predicting future trajectories.
Connected autonomous vehicles (CAVs) promise to enhance safety, efficiency, and sustainability in urban transportation. However, this is contingent upon a CAV correctly predicting the motion of surrounding agents and planning its own motion safely. Doing so is challenging in complex urban environments due to frequent occlusions and interactions among many agents. One solution is to leverage smart infrastructure to augment a CAV's situational awareness; the present work leverages a recently proposed "Self-Supervised Traffic Advisor" (SSTA) framework of smart sensors that teach themselves to generate and broadcast useful video predictions of road users. In this work, SSTA predictions are modified to predict future occupancy instead of raw video, which reduces the data footprint of broadcast predictions. The resulting predictions are used within a planning framework, demonstrating that this design can effectively aid CAV motion planning. A variety of numerical experiments study the key factors that make SSTA outputs useful for practical CAV planning in crowded urban environments.
Game-theoretic inverse learning is the problem of inferring the players' objectives from their actions. We formulate an inverse learning problem in a Stackelberg game between a leader and a follower, where each player's action is the trajectory of a dynamical system. We propose an active inverse learning method for the leader to infer which hypothesis among a finite set of candidates describes the follower's objective function. Instead of using passively observed trajectories like existing methods, the proposed method actively maximizes the differences in the follower's trajectories under different hypotheses to accelerate the leader's inference. We demonstrate the proposed method in a receding-horizon repeated trajectory game. Compared with uniformly random inputs, the leader inputs provided by the proposed method accelerate the convergence of the probability of different hypotheses conditioned on the follower's trajectory by orders of magnitude.
We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation. However, these approaches often remain too data inefficient or unreliable to train on real robotic hardware. In this paper we introduce a novel policy gradient-based policy optimization framework which systematically leverages a (possibly highly simplified) first-principles model and enables learning precise control policies with limited amounts of real-world data. Our approach $1)$ uses the derivatives of the model to produce sample-efficient estimates of the policy gradient and $2)$ uses the model to design a low-level tracking controller, which is embedded in the policy class. Theoretical analysis provides insight into how the presence of this feedback controller addresses overcomes key limitations of stand-alone policy gradient methods, while hardware experiments with a small car and quadruped demonstrate that our approach can learn precise control strategies reliably and with only minutes of real-world data.