An official website of the United States government
This paper presents a hybrid online Partially Observable Markov Decision Process (POMDP) planning system that addresses the problem of autonomous navigation in the presence of multi-modal uncertainty introduced by other agents in the environment. As a particular example, we consider the problem of autonomous navigation in dense crowds of pedestrians and among obstacles. Popular approaches to this problem first generate a path using a complete planner (e.g., Hybrid A*) with ad-hoc assumptions about uncertainty, then use online tree-based POMDP solvers to reason about uncertainty with control over a limited aspect of the problem (i.e. speed along the path). We present a more capable and responsive real-time approach enabling the POMDP planner to control more degrees of freedom (e.g., both speed AND heading) to achieve more flexible and efficient solutions. This modification greatly extends the region of the state space that the POMDP planner must reason over, significantly increasing the importance of finding effective roll-out policies within the limited computational budget that real time control affords. Our key insight is to use multi-query motion planning techniques (e.g., Probabilistic Roadmaps or Fast Marching Method) as priors for rapidly generating efficient roll-out policies for every state that the POMDP planning tree might reach during its limited horizon search. Our proposed approach generates trajectories that are safe and significantly more efficient than the previous approach, even in densely crowded dynamic environments with long planning horizons.
more »
« less
Augmenting Control Policies with Motion Planning for Robust and Safe Multi-robot Navigation
This work proposes a novel method of incorporating calls to a motion planner inside a potential field control policy for safe multi-robot navigation with uncertain dynamics. The proposed framework can handle more general scenes than the control policy and has low computational costs. Our work is robust to uncertain dynamics and quickly finds high-quality paths in scenarios generated from real-world floor plans. In the proposed approach, we attempt to follow the control policy as much as possible, and use calls to the motion planner to escape local minima. Trajectories returned from the motion planner are followed using a path-following controller guaranteeing robustness. We demonstrate the utility of our approach with experiments based on floor plans gathered from real buildings.
more »
« less
- Award ID(s):
- 1830549
- PAR ID:
- 10300746
- Date Published:
- Journal Name:
- IEEE/RSJ International conference on Intelligent Robots and systems (IROS)
- Page Range / eLocation ID:
- 6975 to 6981
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Among approaches for provably safe reinforcement learning, Model Predictive Shielding (MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces, by leveraging a backup policy to ensure safety when the learned policy attempts to take risky actions. However, while MPS can ensure safety both during and after training, it often hinders task progress due to the conservative and task-oblivious nature of backup policies. This paper introduces Dynamic Model Predictive Shielding (DMPS), which optimizes reinforcement learning objectives while maintaining provable safety. DMPS employs a local planner to dynamically select safe recovery actions that maximize both short-term progress as well as long-term rewards. Crucially, the planner and the neural policy play a synergistic role in DMPS. When planning recovery actions for ensuring safety, the planner utilizes the neural policy to estimate long-term rewards, allowing it to observe beyond its short-term planning horizon. Conversely, the neural policy under training learns from the recovery plans proposed by the planner, converging to policies that are both high-performing and safe in practice. This approach guarantees safety during and after training, with bounded recovery regret that decreases exponentially with planning horizon depth. Experimental results demonstrate that DMPS converges to policies that rarely require shield interventions after training and achieve higher rewards compared to several state-of-the-art baselinesmore » « less
-
This paper describes a hierarchical solution consisting of a multi-phase planner and a low-level safe controller to jointly solve the safe navigation problem in crowded, dynamic, and uncertain environments. The planner employs dynamic gap analysis and trajectory optimization to achieve collision avoidance with respect to the predicted trajectories of dynamic agents within the sensing and planning horizon and with robustness to agent uncertainty. To address uncertainty over the planning horizon and real-time safety, a fast reactive safe set algorithm (SSA) is adopted, which monitors and modifies the unsafe control during trajectory tracking. Compared to other existing methods, our approach offers theoretical guarantees of safety and achieves collision-free navigation with higher probability in uncertain environments, as demonstrated in scenarios with 20 and 50 dynamic agents.more » « less
-
This work develops a technique for using robot motion trajectories to create a high quality stochastic dynamics model that is then leveraged in simulation to train control policies with associated performance guarantees. We demonstrate the idea by collecting dynamics data from a 1/5 scale agile ground vehicle, fitting a stochastic dynamics model, and training a policy in simulation to drive around an oval track at up to 6.5 m/s while avoiding obstacles. We show that the control policy can be transferred back to the real vehicle with little loss in predicted performance. We compare this to an approach that uses a simple analytic car model to train a policy in simulation and show that using a model with stochasticity learned from data leads to higher performance in terms of trajectory tracking accuracy and collision probability. Furthermore, we show empirically that simulation-derived performance guarantees transfer to the actual vehicle when executing a policy optimized using a deep stochastic dynamics model fit to vehicle data.more » « less
-
Achieving stable bipedal walking on surfaces with unknown motion remains a challenging control problem due to the hybrid, time-varying, partially unknown dynamics of the robot and the difficulty of accurate state and surface motion estimation. Surface motion imposes uncertainty on both system parameters and non-homogeneous disturbance in the walking robot dynamics. In this paper, we design an adaptive ankle torque controller to simultaneously address these two uncertainties and propose a step-length planner to minimize the required control torque. Typically, an adaptive controller is used for a continuous system. To apply adaptive control on a hybrid system such as a walking robot, an intermediate command profile is introduced to ensure a continuous error system. Simulations on a planar bipedal robot, along with comparisons against a baseline controller, demonstrate that the proposed approach effectively ensures stable walking and accurate tracking under unknown, time-varying disturbances.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/IROS45743.2020.9341153
