Model-free Neural Lyapunov Control for Safe Robot Navigation

Abstract

This paper presents a hierarchical reinforcement learning algorithm constrained by differentiable signal temporal logic. Previous work on logic-constrained reinforcement learning consider encoding these constraints with a reward function, constraining policy updates with a sample-based policy gradient. However, such techniques oftentimes tend to be inefficient because of the significant number of samples required to obtain accurate policy gradients. In this paper, instead of implicitly constraining policy search with sample-based policy gradients, we directly constrain policy search by backpropagating through formal constraints, enabling training hierarchical policies with substantially fewer training samples. The use of hierarchical policies is recognized as a crucial component of reinforcement learning with task constraints. We show that we can stably constrain policy updates, thus enabling different levels of the policy to be learned simultaneously, yielding superior performance compared with training them separately. Experiment results on several simulated high-dimensional robot dynamics and a real-world differential drive robot (TurtleBot3) demonstrate the effectiveness of our approach on five different types of task constraints. Demo videos, code, and models can be found at our project website: https://sites.google.com/view/dscrl.

Stability and Safety Learning Methods for Legged Robots

“…Rabbit biped [43] Locomotion control Marvel biped [44] Navigation control 8-DoF quadruped [45] Walking on 2D stepping stones AMBER-3M biped [46] Walking on 3D stepping stones ANYmal quadruped [47] Navigation control Digit biped [48] Locomotion control AMBER2 7-DoF biped [49] Navigation control 21-DoF biped [50] Locomotion control DURUS 23-DoF biped [51] Walking on 2D stepping stones Rabbit biped [52] Locomotion control Compass-gait walked biped [53] Locomotion control AMBER-3M [65] Navigation Control Laikago [36] Locomotion control Compass-gait walked biped…”

“…The problem of exponentially stabilizing periodic orbits in a special class of hybrid models was addressed in [43] using CLF. The proposed solution based on a variant of CLF that enforces rapid exponential convergence to the zero dynamics [44] to navigate towards a target location, in an environment filled with obstacles. (b) CBF with episodic learning on AMBER-3M biped controlled to walk on stepping stones, the time evolution of the barrier function at episode 0 [45] is reported in the panel where the distance between the robot feet and the stone centres is depicted.…”

“…In the field of model-free deep RL used to solve high-dimensional problems in the presence of unknown dynamics, there is a strong need for safety assurance. In contrast with other approaches encoding safety constraints with rewards [12], the possibility to learn a twin neural Lyapunov function (TNLF) with the control policy in an RL framework was exploited in [44]. The TNLF works as a monitor to select the waypoints that guide the learned controller in combination with the path provided by a planner.…”

“…Application examples for four-legged and two-legged architectures. (a) LF on an 8-DoF quadruped robot controlled with a DDPG algorithm[44] to navigate towards a target location, in an environment filled with obstacles. (b) CBF with episodic learning on AMBER-3M biped controlled to walk on stepping stones, the time evolution of the barrier function at episode 0[45] is reported in the panel where the distance between the robot feet and the stone centres is depicted.…”

Safe Autonomous Exploration and Adaptive Path Planning Strategy Using Signed Distance Field

“…Despite the importance of safety in path planning, the lack of a clear metric to quantify this factor has been noted [7], [40], [47]- [50]. Some studies have reported a qualitative evaluation on safety, such as the absence of collisions [51]. However, considering localization error, information delay and other factors, the passing through the edge of obstacles (though not collided) is also extremely dangerous.…”