Model Predictive Control (MPC) has been widely applied to the motion planning of autonomous vehicles. An MPC-controlled vehicle is required to predict its own trajectories in a finite prediction horizon according to its model. Beyond this, the vehicle should also incorporate the prediction of the trajectory of its nearby vehicles, or target vehicles (TVs) into its decision-making. The conventional trajectory prediction methods, such as the constant-speed-based ones, are too trivial to accurately capture the potential collision risks. In this report, we propose a novel MPC-based motion planning method for an autonomous vehicle with a set of risk-aware constraints. These constraints incorporate the predicted trajectory of a TV learned using a deep-learning-based method. A recurrent neural network (RNN) is used to predict the TV's future trajectory based on its historical data. Then, the predicted TV trajectory is incorporated into the optimization of the MPC of the ego vehicle to generate collision-free motion. Simulation studies are conducted to showcase the prediction accuracy of the RNN model and the collision-free trajectories generated by the MPC.
The driving style of an Autonomous Vehicle (AV) refers to how it behaves and interacts with other AVs. In a multi-vehicle autonomous driving system, an AV capable of identifying the driving styles of its nearby AVs can reliably evaluate the risk of collisions and make more reasonable driving decisions. However, there has not been a consistent definition of driving styles for an AV in the literature, although it is considered that the driving style is encoded in the AV's trajectories and can be identified using Maximum Entropy Inverse Reinforcement Learning (ME-IRL) methods as a cost function. Nevertheless, an important indicator of the driving style, i.e., how an AV reacts to its nearby AVs, is not fully incorporated in the feature design of previous ME-IRL methods. In this paper, we describe the driving style as a cost function of a series of weighted features. We design additional novel features to capture the AV's reaction-aware characteristics. Then, we identify the driving styles from the demonstration trajectories generated by the Stochastic Model Predictive Control (SMPC) using a modified ME-IRL method with our newly proposed features. The proposed method is validated using MATLAB simulation and an off-the-shelf experiment.
Reinforcement learning (RL) for motion planning of multi-degree-of-freedom robots still suffers from low efficiency in terms of slow training speed and poor generalizability. In this paper, we propose a novel RL-based robot motion planning framework that uses implicit behavior cloning (IBC) and dynamic movement primitive (DMP) to improve the training speed and generalizability of an off-policy RL agent. IBC utilizes human demonstration data to leverage the training speed of RL, and DMP serves as a heuristic model that transfers motion planning into a simpler planning space. To support this, we also create a human demonstration dataset using a pick-and-place experiment that can be used for similar studies. Comparison studies in simulation reveal the advantage of the proposed method over the conventional RL agents with faster training speed and higher scores. A real-robot experiment indicates the applicability of the proposed method to a simple assembly task. Our work provides a novel perspective on using motion primitives and human demonstration to leverage the performance of RL for robot applications.
Reinforcement learning (RL) is an effective approach to motion planning in autonomous driving, where an optimal driving policy can be automatically learned using the interaction data with the environment. Nevertheless, the reward function for an RL agent, which is significant to its performance, is challenging to be determined. The conventional work mainly focuses on rewarding safe driving states but does not incorporate the awareness of risky driving behaviors of the vehicles. In this paper, we investigate how to use risk-aware reward shaping to leverage the training and test performance of RL agents in autonomous driving. Based on the essential requirements that prescribe the safety specifications for general autonomous driving in practice, we propose additional reshaped reward terms that encourage exploration and penalize risky driving behaviors. A simulation study in OpenAI Gym indicates the advantage of risk-aware reward shaping for various RL agents. Also, we point out that proximal policy optimization (PPO) is likely to be the best RL method that works with risk-aware reward shaping.
Reinforcement learning demonstrates significant potential in automatically building control policies in numerous domains, but shows low efficiency when applied to robot manipulation tasks due to the curse of dimensionality. To facilitate the learning of such tasks, prior knowledge or heuristics that incorporate inherent simplification can effectively improve the learning performance. This paper aims to define and incorporate the natural symmetry present in physical robotic environments. Then, sample-efficient policies are trained by exploiting the expert demonstrations in symmetrical environments through an amalgamation of reinforcement and behavior cloning, which gives the off-policy learning process a diverse yet compact initiation. Furthermore, it presents a rigorous framework for a recent concept and explores its scope for robot manipulation tasks. The proposed method is validated via two point-to-point reaching tasks of an industrial arm, with and without an obstacle, in a simulation experiment study. A PID controller, which tracks the linear joint-space trajectories with hard-coded temporal logic to produce interim midpoints, is used to generate demonstrations in the study. The results of the study present the effect of the number of demonstrations and quantify the magnitude of behavior cloning to exemplify the possible improvement of model-free reinforcement learning in common manipulation tasks. A comparison study between the proposed method and a traditional off-policy reinforcement learning algorithm indicates its advantage in learning performance and potential value for applications.
Simulation is essential to reinforcement learning (RL) before implementation in the real world, especially for safety-critical applications like robot manipulation. Conventionally, RL agents are sensitive to the discrepancies between the simulation and the real world, known as the sim-to-real gap. The application of domain randomization, a technique used to fill this gap, is limited to the imposition of heuristic-randomized models. We investigate the properties of intrinsic stochasticity of real-time simulation (RT-IS) of off-the-shelf simulation software and its potential to improve the robustness of RL methods and the performance of domain randomization. Firstly, we conduct analytical studies to measure the correlation of RT-IS with the occupation of the computer hardware and validate its comparability with the natural stochasticity of a physical robot. Then, we apply the RT-IS feature in the training of an RL agent. The simulation and physical experiment results verify the feasibility and applicability of RT-IS to robust RL agent design for robot manipulation tasks. The RT-IS-powered robust RL agent outperforms conventional RL agents on robots with modeling uncertainties. It requires fewer heuristic randomization and achieves better generalizability than the conventional domain-randomization-powered agents. Our findings provide a new perspective on the sim-to-real problem in practical applications like robot manipulation tasks.
This paper proposes a novel distributed coverage controller for a multi-agent system with constant-speed unicycle robots (CSUR). The work is motivated by the limitation of the conventional method that does not ensure the satisfaction of hard state- and input-dependent constraints and leads to feasibility issues for multi-CSUR systems. In this paper, we solve these problems by designing a novel coverage cost function and a saturated gradient-search-based control law. Invariant set theory and Lyapunov-based techniques are used to prove the state-dependent confinement and the convergence of the system state to the optimal coverage configuration, respectively. The controller is implemented in a distributed manner based on a novel communication standard among the agents. A series of simulation case studies are conducted to validate the effectiveness of the proposed coverage controller in different initial conditions and with control parameters. A comparison study in simulation reveals the advantage of the proposed method in terms of avoiding infeasibility. The experiment study verifies the applicability of the method to real robots with uncertainties. The development procedure of the method from theoretical analysis to experimental validation provides a novel framework for multi-agent system coordinate control with complex agent dynamics.
Finding an efficient way to adapt robot trajectory is a priority to improve overall performance of robots. One approach for trajectory planning is through transferring human-like skills to robots by Learning from Demonstrations (LfD). The human demonstration is considered the target motion to mimic. However, human motion is typically optimal for human embodiment but not for robots because of the differences between human biomechanics and robot dynamics. The Dynamic Movement Primitives (DMP) framework is a viable solution for this limitation of LfD, but it requires tuning the second-order dynamics in the formulation. Our contribution is introducing a systematic method to extract the dynamic features from human demonstration to auto-tune the parameters in the DMP framework. In addition to its use with LfD, another utility of the proposed method is that it can readily be used in conjunction with Reinforcement Learning (RL) for robot training. In this way, the extracted features facilitate the transfer of human skills by allowing the robot to explore the possible trajectories more efficiently and increasing robot compliance significantly. We introduced a methodology to extract the dynamic features from multiple trajectories based on the optimization of human-likeness and similarity in the parametric space. Our method was implemented into an actual human-robot setup to extract human dynamic features and used to regenerate the robot trajectories following both LfD and RL with DMP. It resulted in a stable performance of the robot, maintaining a high degree of human-likeness based on accumulated distance error as good as the best heuristic tuning.
In this paper, we propose a novel framework using formal methods to synthesize a navigation control strategy for a multi-robot swarm system with automated formation. The main objective of the problem is to navigate the robot swarm toward a goal position while passing a series of waypoints. The formation of the robot swarm should be changed according to the terrain restrictions around the corresponding waypoint. Also, the motion of the robots should always satisfy certain runtime safety requirements, such as avoiding collision with other robots and obstacles. We prescribe the desired waypoints and formation for the robot swarm using a temporal logic (TL) specification. Then, we formulate the transition of the waypoints and the formation as a deterministic finite transition system (DFTS) and synthesize a control strategy subject to the TL specification. Meanwhile, the runtime safety requirements are encoded using control barrier functions, and fixed-time control Lyapunov functions ensure fixed-time convergence. A quadratic program (QP) problem is solved to refine the DFTS control strategy to generate the control inputs for the robots, such that both TL specifications and runtime safety requirements are satisfied simultaneously. This work enlights a novel solution for multi-robot systems with complicated task specifications. The efficacy of the proposed framework is validated with a simulation study.
This paper proposes a novel observer-based disturbance estimation method for high degree-of-freedom Euler-Lagrangian systems using an unknown input-output (UIO) sliding mode observer (SMO). Different from the previous SMO methods, this approach does not assume the matching condition of the disturbances. Besides, compared to the conventional disturbance estimation methods, the proposed method does not require the calculation of the inverse inertia matrices and accurate measurement of system velocities. This advantage resolves the concerns of heavy computational load and amplified noise for practical problems like external torque estimation of high degree-of-freedom manipulators in safe human-robot collaboration. We achieve this by defining a novel linearized model for the Euler-Lagrangian system and designing a sliding-mode-based disturbance observer. The estimation precision of the observer is ensured by the Lyapunov-based stability proof and the equivalent control theory of sliding mode. At the end of this paper, the method is implemented on a seven-degree-of-freedom robot manipulator, and the experimental results confirm its decent performance and potential to be applied in practice.